INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

This neuron never activates (all its activation values are zero), indicating it does not detect any specific feature in the text.

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

.Bad

-0.07

sg

-0.06

Those

-0.06

 summons

-0.06

 Those

-0.06

-chat

-0.06

embedded

-0.06

ANCEL

-0.06

 form

-0.05

 doubling

-0.05

POSITIVE LOGITS

>c

0.07

 전문

0.07

 длитель

0.07

 fileId

0.07

 önemli

0.06

 dioxide

0.06

.define

0.06

 Geile

0.06

 نزد

0.06

něm

0.06

Activations Density 0.138%

numbers

This neuron never activates (all its activation values are zero), indicating it does not detect any specific feature in the text.

No Comments

No Known Activations