claim
active
claim: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-dataPersona vectors do not emerge as a single capability; each persona has its own onset and ceiling ordered by prevalence and behavioral simplicity in pretraining data
Interpretive finding against a unified emergence threshold for all personas
Source paper
extracted_from(2026) · Viktor Moskvoretskii · Dominik Glandorf · Jorge Medina Moreira · Tanja Käser +1
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- First research question driving the study of early persona vector formation
- Replication finding on Apertus confirming early persona formation generalizes across model families
- First of three hypotheses about persona implementation in LLMs, motivating the persona views
- Author's interpretation establishing that persona vectors are not merely general misalignment indicators
- Second research question driving analysis of persona vector geometry and facet evolution
- Interpretive claim about the mechanistic role of persona vectors explaining emergent misalignment
- Core interpretive claim providing mechanistic explanation for early persona formation
- Open question proposed by authors for future work on the dimensionality and structure of persona space