INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

This neuron fires on occurrences of the identifier “isolate” (e.g. V8’s Isolate pointer) in C++ code.

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

 Fraser

-0.07

 сп

-0.06

ipping

-0.06

inding

-0.06

 مرات

-0.06

pt

-0.06

�

-0.06

脸

-0.06

 receptor

-0.06

POSITIVE LOGITS

라도

0.07

'C

0.06

 ราคา

0.06

 дру

0.06

doi

0.06

 организа

0.06

 Ancak

0.06

สมเด

0.06

 lasts

0.06

Om

0.06

Activations Density 0.013%

Code

This neuron fires on occurrences of the identifier “isolate” (e.g. V8’s Isolate pointer) in C++ code.

No Comments

No Known Activations

Code

This neuron fires on occurrences of the identifier “isolate” (e.g. V8’s Isolate pointer) in C++ code.

No Comments

No Known Activations