Cross-Model Persona Vector Transfer

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

• Persona Vector Transition Layerconcept0.792
  Specific attention layer where persona representations undergo sharp directional shift and stabilize, identified via cosine similarity heatmaps
• Persona Vectorconcept0.782
  A linear direction in a language model's activation space that encodes a specific personality trait, enabling monitoring and control of that trait
• Persona Vectors (Chen et al.)framework0.782
  Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
• Persona Modelconcept0.765
  The internal machinery a language model uses to represent and instantiate personas: its learned capacity to simulate, differentiate, and maintain coherent characters
• Persona vectors capture signal specific to their assigned trait, as evidenced by within-trait correlations exceeding cross-trait baselinesclaim0.764
  Author's interpretation establishing that persona vectors are not merely general misalignment indicators
• Persona Vector Extraction via Difference-of-Meansmethod0.757
  Core method for extracting persona vectors by contrasting mean activations under persona-eliciting vs. suppressing prompts
• Persona selection modelframework0.755
  Framework by Marks et al. proposing that models infer a context-appropriate persona for next-token prediction and post-training concentrates distribution around helpful assistant
• Contrastive Persona Vector Extraction Protocolmethod0.752
  Named procedure for extracting persona vectors from mean residual-stream activation differences between trait-expressing and non-expressing responses