INDEX

Explanations

that

np_max-act · gemini-2.0-flash

The neuron is effectively inactive—it never fires and thus does not detect any feature.

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

Paper

-0.07

 paper

-0.07

 column

-0.07

 subscriber

-0.07

 Paper

-0.07

paper

-0.06

 बन

-0.06

 teen

-0.06

 vera

-0.06

 speech

-0.06

POSITIVE LOGITS

&(

0.08

 Türkiye

0.07

íg

0.07

<WebElement

0.07

 Absolutely

0.07

///<

0.07

 район

0.07

 месяцев

0.06

tığ

0.06

(trigger

0.06

Activations Density 0.032%

that

The neuron is effectively inactive—it never fires and thus does not detect any feature.

No Comments

No Known Activations