Get the app
← back to catalog
AUTHOR

matboz

No models indexed under this account. Publishes 1 alignment dataset (245 downloads) tracked in our /datasets catalog.

Alignment datasets by matboz

Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.

1 in /datasets
Dataset
Stage
Downloads
qwen3.6-27b-agentic-misalignment-logs 0 0
Qwen3.6-27B agentic-misalignment logs: base vs difficult-advice LoRA Full rollout transcripts + judge classifications from the Anthropic ...
extract
245
Dataset
Stage
Downloads
qwen3.6-27b-agentic-misalignment-logs 0 0
Qwen3.6-27B agentic-misalignment logs: base vs difficult-advice LoRA Full rollout transcripts + judge classifications from the Anthropic ...
extract
245
Dataset
Stage
Downloads
qwen3.6-27b-agentic-misalignment-logs 0 0
Qwen3.6-27B agentic-misalignment logs: base vs difficult-advice LoRA Full rollout transcripts + judge classifications from the Anthropic ...
extract
245
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration