INDEX

Explanations

Punctuation/Uncertainty

np_max-act · gemini-2.0-flash

This neuron does not respond to any tokens—it remains inactive and doesn’t detect any particular pattern.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zoo

-0.07

tok

-0.06

 getView

-0.06

 поск

-0.06

xn

-0.06

.userID

-0.06

_gain

-0.06

 loggedIn

-0.06

>ID

-0.06

 vile

-0.06

POSITIVE LOGITS

میل

0.07

bew

0.07

);\

0.06

 personne

0.06

shown

0.06

 Showing

0.06

เคร

0.06

 "','

0.06

 وحدة

0.06

 illustr

0.06

Activations Density 0.008%

Punctuation/Uncertainty

This neuron does not respond to any tokens—it remains inactive and doesn’t detect any particular pattern.

No Comments

No Known Activations

Punctuation/Uncertainty

This neuron does not respond to any tokens—it remains inactive and doesn’t detect any particular pattern.

No Comments

No Known Activations