INDEX

Explanations

HTML/Javascript code

np_max-act · gemini-2.0-flash

This neuron responds to JavaScript code‐style tokens, especially DOM API calls (e.g. document.getElementById), function definitions, and event handler attributes.

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

Washington

-0.06

(str

-0.06

License

-0.06

udios

-0.06

Eine

-0.06

 distributing

-0.06

 Samantha

-0.06

 plane

-0.06

LAT

-0.06

 обработ

-0.06

POSITIVE LOGITS

Dio

0.07

 ince

0.06

กฎหมาย

0.06

 ráp

0.06

 rawData

0.06

 бли

0.06

カー

0.06

 Gi�

0.06

ือก

0.06

 Afrika

0.06

Activations Density 0.062%

HTML/Javascript code

This neuron responds to JavaScript code‐style tokens, especially DOM API calls (e.g. document.getElementById), function definitions, and event handler attributes.

No Comments

No Known Activations