INDEX

Explanations

quotation marks

np_max-act · gemini-2.0-flash

This neuron is strongly activated by scholarly study or paper titles (i.e. multi‐word titles often enclosed in quotation marks).

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

SD

-0.07

CIM

-0.07

 при

-0.06

Algorithm

-0.06

visualization

-0.06

Lab

-0.06

KH

-0.06

 {
↵
↵

-0.06

с

-0.06

POSITIVE LOGITS

 무슨

0.07

 tslint

0.07

 Undefined

0.07

 zdravot

0.07

 tyto

0.07

 componentDid

0.06

歲

0.06

 визнач

0.06

ское

0.06

 rencontre

0.06

Activations Density 0.054%

quotation marks

This neuron is strongly activated by scholarly study or paper titles (i.e. multi‐word titles often enclosed in quotation marks).

No Comments

No Known Activations