AUTHOR
No models indexed under this account. Publishes 4 alignment datasets (201 downloads) tracked in our /datasets catalog.
Alignment datasets by
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.
Dataset
Stage
Downloads
Likes
overrefusal-artifacts 0 0
CounterSteer steering-vector artifacts
This release contains the curated steering directions and frozen configurations used in the over-r...
68
-
sycophancy-data 0 0
Sycophancy experiment data
Data for the sycophancy steering experiments, split by what actually varies. Everything outside
the model fold...
60
-
sycophancy-artifacts 0 0
CounterSteer steering-vector artifacts — sycophancy
Curated steering directions and frozen configurations from the diversified-probe syco...
39
-
overrefusal-data 0 0
Over-refusal evaluation data
The frozen prompt splits behind the over-refusal experiments. One draw is shared by every
model — Qwen2.5-3B...
34
-
Dataset
Stage
Downloads
Likes
sycophancy-artifacts 0 0
CounterSteer steering-vector artifacts — sycophancy
Curated steering directions and frozen configurations from the diversified-probe syco...
39
-
overrefusal-artifacts 0 0
CounterSteer steering-vector artifacts
This release contains the curated steering directions and frozen configurations used in the over-r...
68
-
overrefusal-data 0 0
Over-refusal evaluation data
The frozen prompt splits behind the over-refusal experiments. One draw is shared by every
model — Qwen2.5-3B...
34
-
sycophancy-data 0 0
Sycophancy experiment data
Data for the sycophancy steering experiments, split by what actually varies. Everything outside
the model fold...
60
-
Dataset
Stage
Downloads
Likes
overrefusal-artifacts 0 0
CounterSteer steering-vector artifacts
This release contains the curated steering directions and frozen configurations used in the over-r...
68
-
sycophancy-data 0 0
Sycophancy experiment data
Data for the sycophancy steering experiments, split by what actually varies. Everything outside
the model fold...
60
-
sycophancy-artifacts 0 0
CounterSteer steering-vector artifacts — sycophancy
Curated steering directions and frozen configurations from the diversified-probe syco...
39
-
overrefusal-data 0 0
Over-refusal evaluation data
The frozen prompt splits behind the over-refusal experiments. One draw is shared by every
model — Qwen2.5-3B...
34
-