question
active
question:when-do-persona-vectors-first-emerge-during-model-trainingWhen do persona vectors first emerge during model training?
First research question driving the study of early persona vector formation
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.
- Second research question driving analysis of persona vector geometry and facet evolution
- Interpretive finding against a unified emergence threshold for all personas
- Replication finding on Apertus confirming early persona formation generalizes across model families
- Core interpretive claim providing mechanistic explanation for early persona formation
- Persona vectors extracted from base pretraining checkpoints steer fully post-trained OLMo-3-7B-Instructfinding0.791Shows persona directions persist through all alignment stages, answering key part of RQ2
- Supported by comparing persona vector transitions to hidden vector transitions from OpenAssistant data
- How does different post-training data shift a model's position along persona dimensions?question0.781Future work direction: using persona space to study effects of training data on model character
- Key open question about why the persona vector extraction method works beyond correlation