What dimensions of persona are not captured by our extracted role vectors, and how complete is the current persona space mapping?

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

• How does different post-training data shift a model's position along persona dimensions?question0.806
  Future work direction: using persona space to study effects of training data on model character
• We hypothesize that the PC1 axis of role space measures deviation from the Assistant personahypothesis0.801
  Motivates computing the contrast vector as the formal Assistant Axis definition
• 4-19 principal components explain 70% of variance in role persona space across the three models (Gemma 4, Qwen 8, Llama 19)finding0.788
  Demonstrates that persona space is low-dimensional
• We hypothesize that axes of persona differentiation within LLMs are likely already present in base models and inherited from the pre-training corpushypothesis0.782
  Motivated by near-identical PCs for base and instruct Gemma
• The assumption that the Assistant persona corresponds to a linear direction in activation space is likely flawed; some information may be represented nonlinearly or encoded in weights rather than activationsclaim0.761
  Limitation acknowledgment about the adequacy of the linear representation assumption
• Persona Vectors (Chen et al.)framework0.753
  Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
• post-training steers models toward a particular region of persona space but only loosely tethers them to itquote0.748
  Load-bearing summary of the paper's core finding about persona stability
• The two-dimensional subspace reported by Burger et al. (2024) seems to reflect a stage of transition in the model's processing, rather than a universal property of truth directions.quote0.746
  Load-bearing interpretive claim about the layer-specificity of Burger et al.'s finding.