Llama 3.3 70B is the most likely to take on a non-Assistant persona when steered, with even split between human and nonhuman portrayals

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

• LLaMA-2-70B and 13B probes generalize better across datasets than 7B probes across all training sets and probe typesfinding0.831
  Larger models linearly represent more general concepts including truth
• Llama-3.3-70B exhibits internal consistency-checking mechanisms that operate during inferenceclaim0.817
  Central interpretive claim of the paper supported by causal ablation and activation evidence
• Llama-3.3-70B-Instructconcept0.815
  Primary model of interest showing substantial ESR; largest model tested in the study
• Llama-3.3-70B shows multi-attempt rate of 7.4% vs. ≤1.2% for all other models testedfinding0.811
  Supporting finding showing ESR is driven by both higher multi-attempt rates and comparable improvement rates
• Gemma 2 27B is unlikely to take on human personas when steered away from Assistant, preferring nonhuman or theatrical portrayalsfinding0.808
  Model-specific difference in persona susceptibility
• 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 extremesfinding0.808
  Characterizes what is on the far end of the Assistant Axis away from the Assistant
• LLaMA3.1-70Bconcept0.807
  One of four LLMs selected; larger model with D=8192 embedding dimension; analyzed across proportionally aligned layers.
• Llama-3.3-70B corrected response scores 75/100 rather than 100 due to residual steering effects (Snell's law reference)finding0.802
  Illustrative finding that ESR mitigates but does not fully eliminate steering influence