claim
active
claim:personas-are-latent-factors-that-persist-for-many-tokens-so-recent-expression-of-a-persona-predicts-near-future-expressionPersonas are latent factors that persist for many tokens, so recent expression of a persona predicts near-future expression
Author's hypothesis explaining why persona vectors extracted from exhibited-trait activations generalize to causal influence
Source paper
extracted_from(2025) · Chen, Runjin · Arditi, Andy · Sleight, Henry · Evans, Owain +1
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.
- Load-bearing mechanistic conjecture about why persona vectors generalize from extraction to prediction
- Core interpretive claim providing mechanistic explanation for early persona formation
- Open question proposed by authors for future work on the dimensionality and structure of persona space
- Appendix I.
- Conceptual open question about formalizing the persona abstraction beyond the trait level
- Low max cosine similarities.
- Second of three hypotheses about persona implementation, supported by PCA evidence from Lu et al.
- Main monitoring result showing persona vectors can predict behavioral shifts before text generation begins