INDEX

Explanations

code configuration files

np_max-act · gemini-2.0-flash

This neuron fires on JSON object keys (especially the key "snippet," and to a lesser extent other field names like "package" or "command") in configuration‐style data.

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

plemented

-0.07

_args

-0.07

$l

-0.06

 limit

-0.06

/her

-0.06

ールド

-0.06

 brands

-0.06

SA

-0.06

NEW

-0.06

 extracts

-0.06

POSITIVE LOGITS

�

0.06

巧

0.06

 quản

0.06

 miglior

0.06

 μεταξύ

0.06

uggy

0.06

 Surgery

0.06

 tưởng

0.06

 almacen

0.06

 musique

0.06

Activations Density 0.003%

code configuration files

This neuron fires on JSON object keys (especially the key "snippet," and to a lesser extent other field names like "package" or "command") in configuration‐style data.

No Comments

No Known Activations

code configuration files

This neuron fires on JSON object keys (especially the key "snippet," and to a lesser extent other field names like "package" or "command") in configuration‐style data.

No Comments

No Known Activations