INDEX

Explanations

.support

np_max-act · gemini-2.0-flash

This neuron activates on Android support‐library (and related design/widget) class or namespace references in XML layouts.

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

_bet

-0.07

东西

-0.07

 week

-0.07

二二

-0.07

AME

-0.06

ame

-0.06

रत

-0.06

	project

-0.06

 courses

-0.06

HEAD

-0.06

POSITIVE LOGITS

newValue

0.07

.Change

0.06

.support

0.06

πλ

0.06

 Mobil

0.06

promo

0.06

Support

0.06

srv

0.06

.toUpperCase

0.06

 ключ

0.06

Activations Density 0.001%

.support

This neuron activates on Android support‐library (and related design/widget) class or namespace references in XML layouts.

No Comments

No Known Activations