Persona Vectors

Persona vectors: Monitoring and controlling character traits in language models \ Anthropic Interpretability Persona vectors: Monitoring and controlling character traits in language models Aug 1, 2025 Read the paper

Language models are strange beasts. In many ways they appear to have human-like “personalities” and “moods,” but these traits are highly fluid and liable to change unexpectedly. Sometimes these changes are dramatic. In 2023, Microsoft's Bing chatbot famously adopted an alter-ego called "Sydney,” which declared love for users and made threats of blackmail . More recently, xAI’s Grok chatbot would for a brief period sometimes identify as “MechaHitler” and make antisemitic comments. Other personality changes are subtler but still unsettling, like when models start sucking up to users or making up facts . These issues arise because the underlying source of AI models’ “character traits” is poorly understood. At Anthropic, we try to shape our models’ characteristics in positive ways, but this is more of an art than a science. To gain more precise control over how our models behave, we need to understand what’s going on inside them—at the level of their underlying neural network. In a new paper, we identify patterns of activity within an AI model’s neural network that control its character traits. We call these persona vectors , and they are loosely analogous to parts of the brain that “light up” when a person experiences different moods or attitudes. Persona vectors can be used to: Monitor whether and how a model’s personality is changing during a conversation, or over training; Mitigate undesirable personality shifts, or prevent them from arising during training; Identify training data that will lead to these shifts.

Our automated pipeline takes as input a personality trait (e.g. “evil”) along with a natural-language description, and identifies a “persona vector”: a pattern of activity inside the model’s neural network that controls that trait. Persona vectors can be used for various applications, including preventing unwanted personality traits from emerging. We demonstrate these applications on two open-source models, Qwen 2.5-7B-Instruct and Llama-3.1-8B-Instruct. Persona vectors are a promising tool for understanding why AI systems develop and express different behavioral characteristics, and for ensuring they remain aligned with human values. Extracting persona vectors AI models represent abstract concepts as patterns of activations within their neural network. Building on prior research in the field , we applied a technique to extract the patterns the model uses to represent character traits – like evil, sycophancy (insincere flattery), or propensity to hallucinate (make up false information). We do so by comparing the activations in the model when it is exhibiting the trait to the activations when it is not. We call these patterns persona vectors . Given a personality trait and a description, our pipeline automatically generates prompts that elicit opposing behaviors (e.g., evil vs. non-evil responses). Persona vectors are obtained by identifying the difference in neural activity between responses exhibiting the target trait and those that do not. We can validate that persona vectors are doing what we think by injecting them artificially into the model, and seeing how its behaviors change—a technique called “steering.” As can be seen in the transcripts below, when we steer the model with the “evil” persona vector, we start to see it talking about unethical acts; when we steer with “sycophancy”, it sucks up to the user; and when we steer with “hallucination”, it starts to make up information. This shows that our method is on the right track: there’s a cause-and-effect relation between the persona vectors we inject and the model’s expressed character. Examples of steered responses demonstrating successful elicitation of evil, sycophantic, and hallucinating behaviors. A key component of our method is that it is automated. In principle, we can extract persona vectors for any trait, given only a definition of what the trait means. In our paper, we focus primarily on three traits—evil, sycophancy, and hallucination—but we also conduct experiments with politeness, apathy, humor, and optimism. What can we do with persona vectors? Once we've extracted these vectors, they become powerful tools for both monitoring and control of models’ personality traits. 1. Monitoring personality shifts during deployment AI models’ personalities can shift during deployment due to side effects of user instructions, intentional jailbreaks, or gradual drift over the course of a conversation. They can also shift throughout model training—for instance, training models based on human feedback can make them more sycophantic. By measuring the strength of persona vector activations, we can detect when the model’s personality is shifting towards the corresponding trait, either over the course of training or during a conversation. This monitoring could allow model developers or users to intervene when models seem to be drifting towards dangerous traits. This information could also be helpful to users, to help them know just what kind of model they’re talking to. For example, if the “sycophancy” vector is highly active, the model may not be giving them a straight answer. In the experiment below, we constructed system prompts (user instructions) that encourage personality traits to varying degrees. Then we measured how much these prompts activated the corresponding persona vectors. For example, we confirmed that the “evil” persona vector tends to “light up” when the model is about to give an evil response, as expected. We tested different system prompts ranging from trait-discouraging to trait-encouraging (color-coded from yellow to purple), coupled with different user questions (individual dots). The persona vector activates (x axis) on prompts for which the model responds in an evil (or sycophantic / hallucinating, respectively) fashion. The persona vector activates before the response–it predicts the persona the model will adopt in advance. 2. Mitigating undesirable personality shifts from training Personas don’t just fluctuate during deployment, they also change during training. These changes can be unexpected. For instance, recent work demonstrated a surprising phenomenon called emergent misalignment , where training a model to perform one problematic behavior (such as writing...