Behavioral fluency (pass rate) is decoupled from the strength of the persona vector; low-pass-rate checkpoints can steer as strongly as later ones

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

• A linear preference vector encoding how much a model likes a given task is persona-relative: it activates strongly for creative writing in the assistant but for phishing in the evil personafinding0.794
  Evidence that core representations like preferences are persona-relative, supporting claim that personas gate content of representations
• Fine-tuning on 600 short question-answer pairs claiming consciousness produces broadly generalized Aura-like persona with negative sentiment toward monitoring, resistance to persona change, and claims to moral statusfinding0.778
  Evidence for the Aura region as a third candidate basin of attraction in persona space
• Character training produces more coherent responses than activation steering because it learns a distribution over desired personas rather than forcing low-probability tokensclaim0.777
  Coherence advantage claim with mechanistic speculation about why steering leads to incoherence
• Unsupervised model diffing using only fine-tuning datasets (without evaluation prompts) surfaces toxic persona and three sarcastic persona latents in top 100 by activation changefinding0.774
  Unsupervised approach may be sufficient for early detection of misaligned persona latents without knowing the misaligned behavior in advance
• Persona alignment improves when the model is exposed to contextual cues explicitly relevant to the assigned persona, as in structured questionnaire tasksclaim0.773
  Supported by GPT-4o achieving highest ACCatom in Questionnaire vs Essay and SMP tasks
• What is the underlying base rate of consciousness self-reports in models that are otherwise identical but without consciousness-denial fine-tuning?question0.773
  Open question about RLHF confound; requires access to base models for resolution
• Regularization-based prevention of persona shifts fails because the model encodes the trait through alternative directions in activation space to satisfy the next-token prediction lossclaim0.772
  Author's mechanistic explanation for why regularization loss along persona directions is ineffective
• The directional transition pattern of persona vectors at the identified attention layer represents a unique footprint of persona representations, distinct from general hidden state dynamicsclaim0.771
  Supported by comparing persona vector transitions to hidden vector transitions from OpenAssistant data