method
active
method:persona-vector-discoveryPersona vector discovery
Chen et al. method to derive evil/hallucinating/sycophantic vectors.
Neighborhood — ranked by edge-count
Papers (2)
paper
Methods (2)
method
- Persona Vectorsrelated_toDirections in activation space encoding a model's dispositional self-presentation, used as evidence for self-modelling.
- Translates steering vector via weighted average of shared decoder vectors.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- A linear direction in a language model's activation space that encodes a specific personality trait, enabling monitoring and control of that trait
- The paper's reframing: persona vectors read as signals of internal model organization rather than as behavioral controls
- Compositional combination of persona vectors via algebraic operations on activation directions
- Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
- Core method for extracting persona vectors by contrasting mean activations under persona-eliciting vs. suppressing prompts
- The paper's core automated pipeline that takes a trait name and description as input and outputs a corresponding persona vector via contrastive prompting
- Method of extracting persona vectors by contrasting activations when model is prompted to exhibit vs suppress a trait
- Named procedure for extracting persona vectors from mean residual-stream activation differences between trait-expressing and non-expressing responses