INDEX

Explanations

`

np_max-act · gemini-2.0-flash

This neuron never activates (all activation values are zero), so it does not respond to any text features.

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

 обов

-0.06

ordination

-0.06

-even

-0.06

グラ

-0.06

($(

-0.06

放在

-0.06

`_

-0.06

"?

-0.06

POSITIVE LOGITS

cordova

0.07

 yarn

0.06

-form

0.06

 Form

0.06

raci

0.06

entic

0.06

-new

0.06

 vstup

0.06

 Encoding

0.06

 nextState

0.06

Activations Density 0.006%

`

This neuron never activates (all activation values are zero), so it does not respond to any text features.

No Comments

No Known Activations