INDEX

Explanations

scientific methods/materials

np_max-act · gemini-2.0-flash

This neuron is effectively inactive—it does not respond to any tokens.

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

btc

-0.06

,c

-0.06

,f

-0.06

)c

-0.06

กราคม

-0.06

:c

-0.05

 δε

-0.05

 своим

-0.05

.Formatting

-0.05

 sockfd

-0.05

POSITIVE LOGITS

 çift

0.07

COPE

0.07

 ISBN

0.07

Laugh

0.07

service

0.07

Sorted

0.06

 Apocalypse

0.06

 service

0.06

	JLabel

0.06

 LaTeX

0.06

Activations Density 0.003%

scientific methods/materials

This neuron is effectively inactive—it does not respond to any tokens.

No Comments

No Known Activations