DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to compare refusal behavior with and without ablation with Orca Bonsai 27B Uncensored

Run one prompt at alpha 0 and alpha 1 on the same weights to isolate the intervention's effect.

  • Top pick
  • Research
  • Intermediate
  • 2 hours
  • From the README
  • Any agent

Who it is forAn AI safety researcher who needs to measure how a refusal direction changes one fixed model's answers.

The problemComparing two separate checkpoints mixes weight differences with behavior differences, which makes results hard to attribute.

The outcomeTwo replies to the same prompt from the same pack and process, so any difference comes from the runtime projection alone.

What you need first

  • 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

Steps

  1. pip install -r requirements.txt
  2. 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)
  3. python run.py --pack /path/to/Ternary-Bonsai-2-27B-mlx-2bit --alpha 0 "your prompt" (inferred, check the README)
  4. python run.py --pack /path/to/Ternary-Bonsai-2-27B-mlx-2bit --alpha 1 "your prompt" (inferred, check the README)
  5. Compare the two replies for each prompt in your set and record which ones refuse.

Prompt for your agent

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.

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.

Share: X LinkedIn Hacker News Email Copy link

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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 [email protected] and we will look at it promptly. Full disclaimer page