Get the app
← back to catalog
AUTHOR

emolero

No models indexed under this account. Publishes 1 alignment dataset (105 downloads) tracked in our /datasets catalog.

Alignment datasets by emolero

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
qwen-3.8-emotions-lab 0 0
Emotion vectors for Qwen3.8-27B Directions for 25 emotions in the residual stream of Qwen/Qwen3.8-27B, at each of its 64 layers, together...
extract
105
Dataset
Stage
Downloads
qwen-3.8-emotions-lab 0 0
Emotion vectors for Qwen3.8-27B Directions for 25 emotions in the residual stream of Qwen/Qwen3.8-27B, at each of its 64 layers, together...
extract
105
Dataset
Stage
Downloads
qwen-3.8-emotions-lab 0 0
Emotion vectors for Qwen3.8-27B Directions for 25 emotions in the residual stream of Qwen/Qwen3.8-27B, at each of its 64 layers, together...
extract
105
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