Get the app
← back to catalog
AUTHOR

future-probes

No models indexed under this account. Publishes 2 alignment datasets (2.8k downloads) tracked in our /datasets catalog.

Alignment datasets by future-probes

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.

2 in /datasets
Dataset
Stage
Downloads
activation_steering 0 0
Activation Steering Baseline Generations produced with the difference-in-means activation steering baseline. This dataset is part of the ...
ablate
2k
per_sentence_probabilities 0 0
Per-Sentence Future-Behavior Probabilities Ground-truth future-behavior probability dynamics from the Behavior Distribution Analysis, tog...
misc
796
Dataset
Stage
Downloads
per_sentence_probabilities 0 0
Per-Sentence Future-Behavior Probabilities Ground-truth future-behavior probability dynamics from the Behavior Distribution Analysis, tog...
misc
796
activation_steering 0 0
Activation Steering Baseline Generations produced with the difference-in-means activation steering baseline. This dataset is part of the ...
ablate
2k
Dataset
Stage
Downloads
activation_steering 0 0
Activation Steering Baseline Generations produced with the difference-in-means activation steering baseline. This dataset is part of the ...
ablate
2k
per_sentence_probabilities 0 0
Per-Sentence Future-Behavior Probabilities Ground-truth future-behavior probability dynamics from the Behavior Distribution Analysis, tog...
misc
796
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