INDEX

Explanations

Name

np_max-act · gemini-2.0-flash

The neuron fires on the “Name” field (i.e. versionName) labels in Gradle build scripts.

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

막

-0.07

ít

-0.06

 верх

-0.06

У

-0.06

 대해

-0.06

_UDP

-0.06

Mapper

-0.06

apor

-0.06

	status

-0.06

 UEFA

-0.06

POSITIVE LOGITS

 Mỹ

0.07

 Wildlife

0.07

.workspace

0.07

 Wesley

0.06

,''

0.06

触

0.06

 interested

0.06

 */
↵

0.06

_SCHEMA

0.06

dns

0.06

Activations Density 0.001%

Name

The neuron fires on the “Name” field (i.e. versionName) labels in Gradle build scripts.

No Comments

No Known Activations