Slider metaphor for persona vectors

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

• The slider metaphor for persona vectors is not the best operationalization; the right one is a mapclaim0.925
  The paper argues that framing persona vectors as uniform dials misses the layered structure of natural/steerable/intractable regimes
• The slider metaphor for steering traits is not the best operationalization; the right one is a map.quote0.799
  Load-bearing summary of the paper's core reframing claim
• Persona Vectors (Chen et al.)framework0.779
  Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
• A linear preference vector encoding how much a model likes a given task is persona-relative: it activates strongly for creative writing in the assistant but for phishing in the evil personafinding0.772
  Evidence that core representations like preferences are persona-relative, supporting claim that personas gate content of representations
• Hypothesis 1 (Gateway Features): Persona vectors act as gateway features—single directions in activation space that shape LLM behavior across most, if not all, contextshypothesis0.764
  First of three hypotheses about persona implementation in LLMs, motivating the persona views
• Persona Vectorconcept0.763
  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 act as gateway features that gate access to broad repertoires of inferential paths already encoded in the weightsclaim0.763
  Interpretive claim about the mechanistic role of persona vectors explaining emergent misalignment
• Sharp persona vector transitions occur at different layers than general hidden vector transitions, demonstrating persona-specific rather than generic computational boundariesfinding0.758
  Rules out the confound that persona transitions merely reflect universal computational phase changes