INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

The neuron is specifically triggered by code-like tokens—identifiers, keywords, symbols, and other elements from source-code fragments.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bowls

-0.07

PKK

-0.06

 Programm

-0.06

Social

-0.06

 Emblem

-0.06

ynamo

-0.06

ividad

-0.06

 Hazard

-0.06

 Channel

-0.06

 Dirk

-0.06

POSITIVE LOGITS

 ----------------------------------------------------------------

0.07

开奖

0.07

deserialize

0.06

累

0.06

�名

0.06

isLoading

0.06

ิลป

0.06

displayName

0.06

 переход

0.06

Activations Density 0.043%

Code

The neuron is specifically triggered by code-like tokens—identifiers, keywords, symbols, and other elements from source-code fragments.

No Comments

No Known Activations