{
  "id": 18685,
  "url": "https://arxiv.org/abs/2608.11025v1",
  "title": "Data Attribution of Emergent Misalignment with Persona Features",
  "summary": "Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired during pre-training that misaligned fine-tuning amplifies. We ask where these features come from: which pre-training documents activate them, and whether naturally occurring human-written text suffices to induce EM. Using Sparse Autoencoder (SAE) based model diff",
  "authors": "Clemens Vetter, David Kaczér, Lucie Flek, Florian Mai",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-11T15:05:24.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "x-arxiv-red-teaming-query",
  "source_name": "arXiv red teaming query",
  "source_homepage": "https://arxiv.org/a/redteam",
  "ethics_ai_record_url": "https://ethics.ai/record/18685",
  "original_url": "https://arxiv.org/abs/2608.11025v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}