Hypothesis 1 (Gateway Features): Persona vectors act as gateway features—single directions in activation space that shape LLM behavior across most, if not all, contexts

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

• Persona vectors act as gateway features that gate access to broad repertoires of inferential paths already encoded in the weightsclaim0.877
  Interpretive claim about the mechanistic role of persona vectors explaining emergent misalignment
• Hypothesis 2 (Persona Space): Persona vectors jointly compose a persona space; an instance's general dispositional profile is specified by a combination of activations along multiple persona vectorshypothesis0.839
  Second of three hypotheses about persona implementation, supported by PCA evidence from Lu et al.
• Persona vectors do not emerge as a single capability; each persona has its own onset and ceiling ordered by prevalence and behavioral simplicity in pretraining dataclaim0.825
  Interpretive finding against a unified emergence threshold for all personas
• 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 personafinding0.819
  Evidence that core representations like preferences are persona-relative, supporting claim that personas gate content of representations
• There may exist a natural 'persona basis' characterizing the space of all model personas, with correlations between persona vectors predicting co-expression of traitshypothesis0.817
  Open question proposed by authors for future work on the dimensionality and structure of persona space
• The directional transition pattern of persona vectors at the identified attention layer represents a unique footprint of persona representations, distinct from general hidden state dynamicsclaim0.815
  Supported by comparing persona vector transitions to hidden vector transitions from OpenAssistant data
• What is the mechanistic basis for persona vectors extracted from exhibited-trait samples generalizing to causally influence the trait?question0.814
  Key open question about why the persona vector extraction method works beyond correlation
• Are mind-like states and mechanisms in LLMs that operate in persona-relative ways controlled by persona vectors?question0.813
  Identified as an open research direction for future mechanistic interpretability work