Persona vectors as diagnostic instrument

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

• Persona Vectorconcept0.829
  A linear direction in a language model's activation space that encodes a specific personality trait, enabling monitoring and control of that trait
• Persona Vectors (Chen et al.)framework0.823
  Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
• Persona vectors capture signal specific to their assigned trait, as evidenced by within-trait correlations exceeding cross-trait baselinesclaim0.820
  Author's interpretation establishing that persona vectors are not merely general misalignment indicators
• Persona Vector Arithmeticconcept0.815
  Compositional combination of persona vectors via algebraic operations on activation directions
• Persona Vector Extraction via Difference-of-Meansmethod0.798
  Core method for extracting persona vectors by contrasting mean activations under persona-eliciting vs. suppressing prompts
• Persona vectors act as gateway features that gate access to broad repertoires of inferential paths already encoded in the weightsclaim0.792
  Interpretive claim about the mechanistic role of persona vectors explaining emergent misalignment
• Persona vector extraction via contrastive activationmethod0.790
  Method of extracting persona vectors by contrasting activations when model is prompted to exhibit vs suppress a trait
• Contrastive Persona Vector Extraction Protocolmethod0.790
  Named procedure for extracting persona vectors from mean residual-stream activation differences between trait-expressing and non-expressing responses