What distinguishes personas from traits, and do emergence and persistence patterns carry over to compositional or character-level constructs?

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

• Persona representations originate in pretraining, not alignment; they form without explicit supervision as useful features for next-token predictionclaim0.804
  Core interpretive claim providing mechanistic explanation for early persona formation
• There may exist a natural 'persona basis' characterizing the space of all model personas, with correlations between persona vectors predicting co-expression of traitshypothesis0.803
  Open question proposed by authors for future work on the dimensionality and structure of persona space
• Character training operates holistically on the persona, suppressing intuitively opposing traits as well as boosting desired onesclaim0.802
  Claim that models learn the spirit of the constitution, not just its letter, evidenced by suppression of opposing traits
• Personas are latent factors that persist for many tokens, so recent expression of a persona predicts near-future expressionclaim0.797
  Author's hypothesis explaining why persona vectors extracted from exhibited-trait activations generalize to causal influence
• Character traits learned at a qualitatively different depth to those exhibited during mere role-play should overwrite a model's prior on what the assistant behaves like outside of role-playhypothesis0.794
  Driving hypothesis for robustness experiments in Section 3.2
• Do correlations between persona vectors predict co-expression of the corresponding traits?question0.792
  Specific open question about the predictive value of persona vector geometry for behavioral co-expression
• Persona vectors do not emerge as a single capability; each persona has its own onset and ceiling ordered by prevalence and behavioral simplicity in pretraining dataclaim0.790
  Interpretive finding against a unified emergence threshold for all personas
• Two components are important to shaping model character: persona construction and persona stabilizationclaim0.789
  Overarching conceptual framework the paper introduces for model safety