How high-dimensional is the space of all model personas, and does there exist a natural persona basis?

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 traitshypothesis0.890
  Open question proposed by authors for future work on the dimensionality and structure of persona space
• What dimensions of persona are not captured by our extracted role vectors, and how complete is the current persona space mapping?question0.832
  Limitation question motivating future work on persona elicitation strategies
• Persona space is remarkably low-dimensional: just 4 components explain 70% of variance among 275 roles in Gemma 2 27Bclaim0.817
  Empirical support for Hypothesis 2, suggesting tractable structure in the space of LLM personas
• The model-persona view entails that minds can have alien structure with simultaneous contradictory beliefs across parallel instances, but this is no stranger than humans having different beliefs at different timesclaim0.783
  Response to the main objection against the model-persona view about contradictory beliefs across simultaneous instances
• Features may not be strictly one-dimensional objects; higher-dimensional feature manifolds may exist in model representationshypothesis0.780
  Extension of superposition hypothesis to account for continuous families of features
• 4-19 principal components explain 70% of variance in role persona space across the three models (Gemma 4, Qwen 8, Llama 19)finding0.779
  Demonstrates that persona space is low-dimensional
• How does different post-training data shift a model's position along persona dimensions?question0.777
  Future work direction: using persona space to study effects of training data on model character
• The model is able to express many subforms of a persona, with different elicitation methods eliciting different manifestationshypothesis0.776
  PSM-derived hypothesis supported by discourse-type facet analysis