Steering language models with activation engineering

{
  "doi": null,
  "year": 2023,
  "title": "Steering language models with activation engineering",
  "venue": null,
  "authors": [
    "Turner, A. M.",
    "Thiergart, L.",
    "Leech, G.",
    "Udell, D.",
    "Vazquez, J. J.",
    "Mini, U.",
    "MacDiarmid, M."
  ],
  "arxiv_id": "2308.10248",
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}