question

active

question:do-correlations-between-persona-vectors-predict-co-expression-of-the-corresponding-traits

Do correlations between persona vectors predict co-expression of the corresponding traits?

Specific open question about the predictive value of persona vector geometry for behavioral co-expression

Source paper

extracted_from

Persona Vectors: Monitoring and Controlling Character Traits in Language Models

(2025) · Chen, Runjin · Arditi, Andy · Sleight, Henry · Evans, Owain +1

Neighborhood — ranked by edge-count

Papers (1)

paper

Persona Vectors: Monitoring and Controlling Character Traits in Language Models
mentions

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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 traitshypothesis0.877
Open question proposed by authors for future work on the dimensionality and structure of persona space
Persona vectors capture signal specific to their assigned trait, as evidenced by within-trait correlations exceeding cross-trait baselinesclaim0.822
Author's interpretation establishing that persona vectors are not merely general misalignment indicators
What is the mechanistic basis for persona vectors extracted from exhibited-trait samples generalizing to causally influence the trait?question0.818
Key open question about why the persona vector extraction method works beyond correlation
Projection of last prompt token onto persona vector correlates r=0.75–0.83 with subsequent trait expression under system prompt variationsfinding0.816
Main monitoring result showing persona vectors can predict behavioral shifts before text generation begins
Hypothesis 2 (Persona Space): Persona vectors jointly compose a persona space; an instance's general dispositional profile is specified by a combination of activations along multiple persona vectorshypothesis0.794
Second of three hypotheses about persona implementation, supported by PCA evidence from Lu et al.
What distinguishes personas from traits, and do emergence and persistence patterns carry over to compositional or character-level constructs?question0.792
Conceptual open question about formalizing the persona abstraction beyond the trait level
Personas are latent factors that persist for many tokens, so recent expression of a persona predicts near-future expressionclaim0.788
Author's hypothesis explaining why persona vectors extracted from exhibited-trait activations generalize to causal influence
Cosine Similarity of Persona Vectorsconcept0.786
Geometric measure used to track persona vector drift and stability across checkpoints