Article
Activation Steering With Mean Response Probes : A Case Study In Suppressing Sycophancy In Language Models During TTC
•
1
Tensor-Slayer PRO
TensorSlay
AI & ML interests
None yet
Recent Activity
published
an
article
about 1 month ago
Activation Steering With Mean Response Probes : A Case Study In Suppressing Sycophancy In Language Models During TTC
published
an
article
about 2 months ago
Exploring Direct Tensor Manipulation in Language Models: A Case Study in Binary-Level Model Enhancement
updated
a model
4 months ago
TensorSlay/qwen-0.6b-arpo-sft-adamw
Organizations
published
an
article
about 1 month ago
published
an
article
about 2 months ago
Article
Exploring Direct Tensor Manipulation in Language Models: A Case Study in Binary-Level Model Enhancement
•
4