Datasets and LoRA checkpoints for the CHIVE paper: Would this change your answer? Predicting the Effects of Prompt Edits on LLM Behavior in the Wild.
Adam Karvonen
adamkarvonen
AI & ML interests
None yet
Recent Activity
published a model 1 day ago
adamkarvonen/qwen3.8-27b-nla-L42 updated a model 2 days ago
adamkarvonen/qwen3.8-27b-nla-L42 updated a model 16 days ago
adamkarvonen/qwen3.8-27b-loan-rlOrganizations
None yet
Activation Oracles
-
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B
Text Generation • Updated • 1.24k • 1 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it
Text Generation • Updated • 61 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Qwen3-1_7B
Text Generation • Updated • 247 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Llama-3_2-1B-Instruct
Text Generation • Updated • 62
CHIVE: Counterfactual Hypothesis Investigation Via Edits
Datasets and LoRA checkpoints for the CHIVE paper: Would this change your answer? Predicting the Effects of Prompt Edits on LLM Behavior in the Wild.
Activation Oracles
-
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B
Text Generation • Updated • 1.24k • 1 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it
Text Generation • Updated • 61 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Qwen3-1_7B
Text Generation • Updated • 247 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Llama-3_2-1B-Instruct
Text Generation • Updated • 62
models 259
adamkarvonen/qwen3.8-27b-nla-L42
Text Generation • Updated
adamkarvonen/qwen3.8-27b-loan-rl
Updated
adamkarvonen/qwen3.6-27b-loan-rl
Updated
adamkarvonen/qwen3-8b-loan-rl
Updated
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3.6-27B
Updated • 90
adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 41
adamkarvonen/llama3_1_8b_on_qwen3_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 6
adamkarvonen/qwen3_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 39
adamkarvonen/llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 14
adamkarvonen/qwen3p5_397b_selfexpl_e3_kl0
Text Generation • Updated • 9
datasets 20
adamkarvonen/chive-data
Updated • 1.53k • 2
adamkarvonen/inf_ver
Updated • 11
adamkarvonen/sae_max_acts
Updated • 331
adamkarvonen/introspection_data
Updated • 6
adamkarvonen/llama_8b_introspect_lora
Updated • 1
adamkarvonen/bias_eval
Updated • 4
adamkarvonen/resumes
Viewer • Updated • 2.48k • 6 • 1
adamkarvonen/sae_bench_results_0125
Updated • 899 • 1
adamkarvonen/ravel_prompts
Updated • 438
adamkarvonen/matryoshka_ablation_results_0125
Preview • Updated • 82