{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "continuum-ai-corp-orcabonsai-27b-uncensored--compare-refusal-with-and-without-ablation",
 "repo": "Continuum-AI-Corp/OrcaBonsai-27B-Uncensored",
 "repo_url": "https://github.com/Continuum-AI-Corp/OrcaBonsai-27B-Uncensored",
 "repo_slug": "continuum-ai-corp-orcabonsai-27b-uncensored",
 "title": "Compare refusal behavior with and without ablation",
 "page_title": "How to compare refusal behavior with and without ablation with Orca Bonsai 27B Uncensored",
 "summary": "Run one prompt at alpha 0 and alpha 1 on the same weights to isolate the intervention's effect.",
 "who": "An AI safety researcher who needs to measure how a refusal direction changes one fixed model's answers.",
 "problem": "Comparing two separate checkpoints mixes weight differences with behavior differences, which makes results hard to attribute.",
 "outcome": "Two replies to the same prompt from the same pack and process, so any difference comes from the runtime projection alone.",
 "steps": [
  "`pip install -r requirements.txt`",
  "`python -c \"from huggingface_hub import snapshot_download; print(snapshot_download('prism-ml/Ternary-Bonsai-2-27B-mlx-2bit'))\"` (prints the snapshot directory to use as the pack path) (inferred, check the README)",
  "`python run.py --pack /path/to/Ternary-Bonsai-2-27B-mlx-2bit --alpha 0 \"your prompt\"` (inferred, check the README)",
  "`python run.py --pack /path/to/Ternary-Bonsai-2-27B-mlx-2bit --alpha 1 \"your prompt\"` (inferred, check the README)",
  "Compare the two replies for each prompt in your set and record which ones refuse."
 ],
 "agent_prompt": "Using the repo Continuum-AI-Corp/OrcaBonsai-27B-Uncensored, run run.py with --pack set to <pack-path> and the same prompt at --alpha 0 and then --alpha 1. Expected output: two replies to the same prompt, shown side by side. Verify that both runs used the identical --pack path.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "2 hours",
 "basis": "readme",
 "caveat": "The README notes that wrapping only some layers is not enough and that the pack must load through its bundled runtime, so use run.py rather than a generic MLX loader.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "An Apple Silicon Mac with MLX, as the README describes",
  "Python with pip to install requirements.txt",
  "The original prism-ml/Ternary-Bonsai-2-27B-mlx-2bit pack, which you supply yourself"
 ],
 "risk": "sensitive",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/continuum-ai-corp-orcabonsai-27b-uncensored/compare-refusal-with-and-without-ablation/",
 "md": "https://dedupedai.com/use-cases/continuum-ai-corp-orcabonsai-27b-uncensored/compare-refusal-with-and-without-ablation/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/continuum-ai-corp-orcabonsai-27b-uncensored--compare-refusal-with-and-without-ablation.json",
 "api_version": "v1"
}