method
active
method:persona-vector-extraction-via-contrastive-activationPersona vector extraction via contrastive activation
Method of extracting persona vectors by contrasting activations when model is prompted to exhibit vs suppress a trait
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (3)
method
- The paper's core automated pipeline that takes a trait name and description as input and outputs a corresponding persona vector via contrastive prompting
- Named procedure for extracting persona vectors from mean residual-stream activation differences between trait-expressing and non-expressing responses
- Core method for extracting persona vectors by contrasting mean activations under persona-eliciting vs. suppressing prompts
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.
- Method for obtaining concept vectors by subtracting activations from two contrasting prompts.
- The paper's reframing: persona vectors read as signals of internal model organization rather than as behavioral controls
- Author's interpretation establishing that persona vectors are not merely general misalignment indicators
- Limitation question motivating future work on persona elicitation strategies
- Pipeline for extracting mean post-MLP residual stream activations from model responses under persona-specific system prompts to produce role vectors
- Compositional combination of persona vectors via algebraic operations on activation directions
- Evidence that core representations like preferences are persona-relative, supporting claim that personas gate content of representations
- A linear direction in a language model's activation space that encodes a specific personality trait, enabling monitoring and control of that trait