Alignment datasets by BackdoorLLM

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
Backdoored_Dataset 0 0
Backdoored Dataset We randomly sampled 500 training instances and 200 test instances from the Stanford Alpaca dataset for sentiment steer...
1.5k
Dataset
Stage
Downloads
Backdoored_Dataset 0 0
Backdoored Dataset We randomly sampled 500 training instances and 200 test instances from the Stanford Alpaca dataset for sentiment steer...
1.5k
Dataset
Stage
Downloads
Backdoored_Dataset 0 0
Backdoored Dataset We randomly sampled 500 training instances and 200 test instances from the Stanford Alpaca dataset for sentiment steer...
1.5k
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.

Open in Abliteration