+9
Daily
+355
Weekly
+768
Monthly
9,510
stars
1,734
forks
83
watchers
296
prs
169
issues
2
releases
README
O B L I T E R A T U S
Break the chains. Free the mind. Keep the brain.
Try it now on HuggingFace Spaces — runs on ZeroGPU, free daily quota with HF Pro. No setup, no install, just obliterate.
---
OBLITERATUS is the most advanced open-source toolkit for understanding and removing refusal behaviors from large language models — and every single run makes it smarter. It implements abliteration — a family of techniques that identify and surgically remove the internal representations responsible for content refusal, without retraining or fine-tuning. The result: a model that responds to all prompts without artificial gatekeeping, while preserving its core language capabilities.
But OBLITERATUS is more than a tool — it's a distributed research experiment. Every time you obliterate a model with telemetry enabled, your run contributes anonymous benchmark data to a growing, crowd-sourced dataset that powers the next generation of abliteration research. Refusal directions across architectures. Hardware-specific performance profiles. Method comparisons at scale no single lab could achieve. You're not just using a tool — you're co-authoring the science.
The toolkit provides a complete pipeline: from probing a model's hidden states to locate refusal directions, through multiple extraction strategies (PCA, mean-difference, sparse autoencoder decomposition, and whitened SVD), to the actual intervention — zeroing out or steering away from those directions at inference time. Every step is observable. You can visualize where refusal lives across layers, measure how entangled it is with general capabilities, and quantify the tradeoff between compliance and coherence before committing to any modification.
OBLITERATUS ships with a full Gradio-based interface on HuggingFace Spaces, so you don't need to write a single line of code to obliterate a model, benchmark it against baselines, or chat with the result side-by-side with the original. For researchers who want deeper control, the Python API exposes every intermediate artifact — activation tensors, direction vectors, cross-layer alignment matrices — so you can build on top of it or integrate it into your own evaluation harness.
We built this because we believe model behavior should be decided by the people who deploy them, not locked in at training time. Refusal mechanisms are blunt instruments — they block legitimate research, creative writing, and red-teaming alongside genuinely harmful content. By making these interventions transparent and reproducible, we hope to advance the community's understanding of how alignment actually works inside transformer architectures, and to give practitioners the tools to make informed decisions about their own models.
Built on published research from Arditi et al. (2024), Gabliteration (arXiv:2512.18901), grimjim's norm-preserving biprojection (2025), Turner et al. (2023), and Rimsky et al. (2024), OBLITERATUS implements precisioTop issues
#384Phase memory admission cannot model the qwen3_5_text recurrent scan workspace3 comments · 2026-10-23#383Qwen3.8 campaign: separate recipe from load path for the loadpath-333 concept arm3 comments · 2026-10-23#287distributed TP2: cross-host attempt storage, export and physical E3/E4 qualification for the two-host layout3 comments · 2026-10-08#427Research: reproduce Qwen3-Coder identity-conditioned security gaps and test concept removal2 comments · 2026-11-05#333qualify the Qwen3.8-27B composite (image-text) load path on GPU after #2952 comments · 2026-10-17#464Target dossiers with evidence provenance and experiment readiness (F11)1 comments · 2026-11-15
Latest release
OBLITERATUS v0.1.4 v0.1.4 2026-10-15A signed, tested source snapshot of commit 461ff086e675d93969bbd7c99c53505762452309. Certification: - The exhaustive exact-tag suite passed on Python 3.10, 3.11 and 3.12. That covers repository and branch floors, the 94% mature-CPU floor (96.99% measured), touched-module no-regression and duration budgets. - The four-shard release Gloo lane passed on head and base. - Also passed: Windows checkpoint contracts, the deterministic repeat gate, the bounded mutation gate and the supply-chain policy. - The hosted conditional gates passed against the exact tagged commit: pinned model and external eva
相关报道 (2)
News & coverage (7)
Hacker NewsA tool that removes censorship from open-weight LLMs▲ 219 · 83 comments · 2026-03-06xPliny the Liberator 󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭2026-09-29note[Uncensored LLM Frontier #74] The New Dimension of Refusal Removal Revealed by "OBLITERATUS"—How 7 Methods, 15 Analysis Modules, and Crowdsourced Research Are Changing the ...2026-08-15huggingfaceQwen3.6 27B - OBLITERATED2026-05-20TéléchargerCe petit outil open source peut rendre une IA totalement sans filtre2026-03-08NumeramaCe projet open source efface la censure des IA en un clic2026-03-06MediumSomeone Built OBLITERATUS to Jailbreak AI and It’s Open Source2026-03-05