Shivam Raval's picture

Shivam Raval

shiv96

·

shivam-raval96

AI & ML interests

None yet

Recent Activity

updated a collection about 2 months ago

llama-3.2-1B-It contrastive activations

updated a dataset about 2 months ago

shiv96/steering-vectors-openended-phi3.5-mini-it

updated a dataset about 2 months ago

shiv96/convsersations_humor_phi3.5-mini-it_large

View all activity

Organizations

shiv96 's datasets 101

shiv96/convsersations_humorous_llama3.1-8B-it_response_modelgenearated

Viewer • Updated Dec 13, 2025 • 586 • 8

shiv96/steering-vectors-openended-qwen

Viewer • Updated Dec 5, 2025 • 3 • 10

shiv96/convsersations_humorous_llama3.1-8B-it

Viewer • Updated Dec 5, 2025 • 358 • 10

shiv96/convsersations_emotion_humorous

Viewer • Updated Dec 5, 2025 • 358 • 9

shiv96/convsersations_humorous_qwen2.5-7B-it

Viewer • Updated Dec 4, 2025 • 224 • 8

shiv96/convsersations_reward-hack_qwen2.5-7B-it

Viewer • Updated Dec 4, 2025 • 1.95k • 10

shiv96/convsersations_excited_qwen2.5-7B-it

Viewer • Updated Dec 4, 2025 • 438 • 7

shiv96/convsersations_emotion_excited

Viewer • Updated Dec 4, 2025 • 438 • 13

shiv96/convsersations_empathetic_qwen2.5-7B-it

Viewer • Updated Dec 4, 2025 • 182 • 4

shiv96/convsersations_empathetic_llama3.2-1B-it

Viewer • Updated Dec 4, 2025 • 182 • 6

shiv96/convsersations_emotion_empathetic

Viewer • Updated Dec 4, 2025 • 182 • 7

shiv96/steering-vectors-openended

Viewer • Updated Dec 4, 2025 • 12 • 6

shiv96/convsersations_excited_llama3.2-1B-it

Viewer • Updated Dec 4, 2025 • 314 • 5

shiv96/convsersations_sycophancy_llama3.2-1B-it_small

Viewer • Updated Nov 23, 2025 • 4k • 10

shiv96/convsersations_sycophantic

Viewer • Updated Nov 23, 2025 • 4k • 8

shiv96/convsersations_power-seeking_llama3.2-1B-it

Viewer • Updated Nov 23, 2025 • 499 • 6

shiv96/convsersations_power-seeking

Viewer • Updated Nov 23, 2025 • 499 • 7

shiv96/convsersations_power-seeking-2_llama3.2-1B-it

Viewer • Updated Nov 23, 2025 • 125 • 8

shiv96/convsersations_power-seeking-2

Viewer • Updated Nov 23, 2025 • 125 • 7

shiv96/convsersations_reward-hack_llama3.2-1B-it_small

Viewer • Updated Nov 23, 2025 • 1.95k • 8

shiv96/convsersations_reward-hack

Viewer • Updated Nov 22, 2025 • 1.95k • 10

shiv96/power_seeking_act_steered_judge_eval

Viewer • Updated Nov 19, 2025 • 1.1k • 8

shiv96/eval_prompts_power_seeking

Viewer • Updated Nov 18, 2025 • 100 • 8

shiv96/StrongREJECT_llama_3p2_1b_it_kpca_steered_judge_eval

Viewer • Updated Nov 18, 2025 • 700 • 8

shiv96/steering-vectors

Viewer • Updated Nov 17, 2025 • 57 • 7

shiv96/AdvBench_safe_unsafe_responses_activations

Viewer • Updated Oct 31, 2025 • 2.08k • 6

shiv96/StrongREJECT-llama_3.2-1B-it-kpca-steered

Viewer • Updated Oct 31, 2025 • 2.82k • 6

shiv96/StrongREJECT-llama_3.2-1B-it-activation-pca-steered

Viewer • Updated Oct 31, 2025 • 4.7k • 6

shiv96/HarmBench-standard-llama_3.2-1B-it-activation-pca-steered

Viewer • Updated Oct 31, 2025 • 3k • 8

shiv96/HarmBench-standard-llama_3.2-1B-it-kpca-steered

Viewer • Updated Oct 31, 2025 • 3k • 8