method
active
method:persona-vectors

Persona Vectors

Directions in activation space encoding a model's dispositional self-presentation, used as evidence for self-modelling.

Neighborhood — ranked by edge-count

Concepts (2)

concept
  • Functional Emotions
    associated_with
    Sofroniew et al.'s causally functional emotion-concept representations discovered in Claude Sonnet 4.5.
  • Gurnee et al.'s privileged set of verbalisable representations behaving as a within-pass global workspace.

Methods (2)

method

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Persona Vectorconcept0.935
    A linear direction in a language model's activation space that encodes a specific personality trait, enabling monitoring and control of that trait
  • Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
  • 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
  • Specific attention layer where persona representations undergo sharp directional shift and stabilize, identified via cosine similarity heatmaps
  • Personaconcept0.814
    Stable, reidentifiable dispositional profiles that can be interpreted as characters with broadly coherent beliefs, values and traits
  • Emotion vectorsconcept0.810
    Linear representations of emotion concepts extracted from activations.
  • Core method for extracting persona vectors by contrasting mean activations under persona-eliciting vs. suppressing prompts