Pairwise correlation of role loadings on PC2 is 0.89 between Qwen and Llama; Gemma differs (similarity <0.61) from others on PC2

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

• Pairwise correlation of role loadings on PC1 exceeds 0.92 across all model pairs, indicating remarkably high similarity of the Assistant Axis across Gemma, Qwen, and Llamafinding0.892
  Shows the leading component of persona space is model-universal
• Base and instruct Gemma 2 27B role PCs have cosine similarities of 0.93, 0.87, 0.83 for the top 3 PCs respectively; role vector cosine similarities >0.99 for every role pairfinding0.796
  Shows persona space axes are inherited from pre-training, not solely created by post-training
• Gemma's Assistant appears emotionally regulated and systematic; Qwen appears pedagogical and thoughtful; Llama appears socially intelligent and warmclaim0.793
  Model-specific characterizations of what the Assistant persona looks like across different models
• 4-19 principal components explain 70% of variance in role persona space across the three models (Gemma 4, Qwen 8, Llama 19)finding0.787
  Demonstrates that persona space is low-dimensional
• When steered to the extreme away from the Assistant, Llama and Gemma shift to a theatrical persona characterized by mystical, poetic prose; Qwen more often hallucinates a human persona at extremesfinding0.764
  Characterizes what is on the far end of the Assistant Axis away from the Assistant
• Qwen3-32B achieves a skill-load rate of 0.251, while Opus 4.6, Sonnet 4.6, and Qwen3-235B achieve SLR of 0.957–0.961finding0.746
  Quantifies harness activation failure for weak-tier models vs. strong-tier models
• Pairwise similarity of trait PC1 across all three models is >0.81; no pairwise correlation in top 3 trait PCs is below 0.70finding0.745
  Shows trait space has more cross-model consistency than role space beyond PC1
• The difficulty boundary for truth directions replicates across all four tested models (Llama-3.2-3B, Llama-3.1-8B, Gemma-2-2b, Gemma-2-9b); generalization to F3-F5 remains consistently low regardless of model size or family.finding0.743
  Establishes generalizability of the core difficulty-boundary finding across model families.