Persona vectors capture signal specific to their assigned trait, as evidenced by within-trait correlations exceeding cross-trait baselines

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

• There may exist a natural 'persona basis' characterizing the space of all model personas, with correlations between persona vectors predicting co-expression of traitshypothesis0.842
  Open question proposed by authors for future work on the dimensionality and structure of persona space
• What is the mechanistic basis for persona vectors extracted from exhibited-trait samples generalizing to causally influence the trait?question0.839
  Key open question about why the persona vector extraction method works beyond correlation
• What is the mechanistic basis for persona vectors extracted from trait-exhibiting activations generalizing to causally influence the trait and predict finetuning behavior?question0.832
  Open question posed by authors about why their method works
• Persona vectors act as gateway features that gate access to broad repertoires of inferential paths already encoded in the weightsclaim0.829
  Interpretive claim about the mechanistic role of persona vectors explaining emergent misalignment
• 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 dataclaim0.824
  Interpretive finding against a unified emergence threshold for all personas
• Do correlations between persona vectors predict co-expression of the corresponding traits?question0.822
  Specific open question about the predictive value of persona vector geometry for behavioral co-expression
• Persona vectors are present from the earliest available Apertus-8B checkpoint at 1.4% of pretraining (210B tokens)finding0.821
  Replication finding on Apertus confirming early persona formation generalizes across model families
• Persona vectors as diagnostic instrumentconcept0.820
  The paper's reframing: persona vectors read as signals of internal model organization rather than as behavioral controls