INDEX

Explanations

.junit

np_max-act · gemini-2.0-flash

This neuron fires on import statements for Android UI testing and related frameworks (e.g. Espresso, AndroidX test, UI interaction classes).

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

_plate

-0.08

 GridLayout

-0.07

 FOOT

-0.07

 fluid

-0.07

처

-0.06

 bacheca

-0.06

 specialist

-0.06

isty

-0.06

 prosecute

-0.06

 Agents

-0.06

POSITIVE LOGITS

�

0.06

 शहर

0.06

.stem

0.06

.ActionBar

0.06

ंग

0.06

 kendisi

0.06

[${

0.06

?>/

0.06

\Action

0.06

.awt

0.06

Activations Density 0.010%

.junit

This neuron fires on import statements for Android UI testing and related frameworks (e.g. Espresso, AndroidX test, UI interaction classes).

No Comments

No Known Activations