INDEX

Explanations

notes

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the word “note,” especially as part of the brand name “Evernote.”

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

 드라마

-0.07

ificaciones

-0.07

.Fixed

-0.07

HIP

-0.06

алом

-0.06

 Medicine

-0.06

 yıldız

-0.06

 бак

-0.06

roduction

-0.06

duplicate

-0.06

POSITIVE LOGITS

Note

0.07

 UserService

0.06

 lấy

0.06

げ

0.06

(":/

0.06

Orc

0.06

 spills

0.06

GetCurrent

0.06

 getSession

0.06

 checkBox

0.06

Activations Density 0.003%

notes

This neuron activates on occurrences of the word “note,” especially as part of the brand name “Evernote.”

No Comments

No Known Activations

notes

This neuron activates on occurrences of the word “note,” especially as part of the brand name “Evernote.”

No Comments

No Known Activations