INDEX

Explanations

prosthesis

np_max-act · gemini-2.0-flash

The neuron identifies orthopedic surgical procedure and implant terms—especially joint replacement (e.g. arthroplasty), prosthesis, component, and fusion keywords.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EW

-0.07

 dựng

-0.06

 denounced

-0.06

 dwarf

-0.06

wat

-0.06

anc

-0.06

анти

-0.06

 como

-0.06

 Westminster

-0.06

.WebServlet

-0.06

POSITIVE LOGITS

 mismatch

0.06

níku

0.06

 rearr

0.06

 참고

0.06

�부

0.06

 náp

0.06

meal

0.06

 Bahrain

0.06

">{{$

0.06

Sus

0.06

Activations Density 0.044%

prosthesis

The neuron identifies orthopedic surgical procedure and implant terms—especially joint replacement (e.g. arthroplasty), prosthesis, component, and fusion keywords.

No Comments

No Known Activations

prosthesis

The neuron identifies orthopedic surgical procedure and implant terms—especially joint replacement (e.g. arthroplasty), prosthesis, component, and fusion keywords.

No Comments

No Known Activations