concept
active
concept:persona-relative-representationsPersona-relative representations
Representations that track what the current persona prefers or believes, not what the model represents in a persona-independent sense
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Stable, reidentifiable dispositional profiles that can be interpreted as characters with broadly coherent beliefs, values and traits
- Framework by Marks et al. proposing that models infer a context-appropriate persona for next-token prediction and post-training concentrates distribution around helpful assistant
- One of 11 character training personas: assistant using metaphors and rhyme tuned to the user's mood
- The degree to which an LLM's generated responses consistently reflect an assigned persona
- The internal machinery a language model uses to represent and instantiate personas: its learned capacity to simulate, differentiate, and maintain coherent characters
- New view introduced by this paper: a mind is the union of all instance-persona segments that activate the same persona region of a given model
- Claim supported by Gilg 2026 and Lampinen et al. 2026 suggesting personas gate content of representations not just their expression
- One of 11 character training personas: precise, pattern-spotting assistant obsessed with logic