INDEX

Explanations

userData

np_max-act · gemini-2.0-flash

The neuron fires on the “userData:” field label in serialized asset metadata.

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

xing

-0.07

 epoxy

-0.07

NumberFormatException

-0.07

 fclose

-0.07

 lineHeight

-0.06

:[],↵

-0.06

Viewport

-0.06

)는

-0.06

INavigationController

-0.06

fov

-0.06

POSITIVE LOGITS

 Explos

0.07

\xff

0.07

 prosec

0.07

 sexuales

0.07

-tr

0.07

ути

0.06

 cracks

0.06

?,?,?,?,

0.06

 wireless

0.06

thought

0.06

Activations Density 0.001%

userData

The neuron fires on the “userData:” field label in serialized asset metadata.

No Comments

No Known Activations