INDEX

Explanations

Date and time formatting

np_max-act · gemini-2.0-flash

This neuron does not detect any pattern—it never activates for any token.

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

ुरस

-0.07

 dungeon

-0.06

isors

-0.06

 dairy

-0.06

екотор

-0.06

XMLElement

-0.06

JOB

-0.06

Hu

-0.06

pta

-0.06

 Leer

-0.06

POSITIVE LOGITS

़े

0.06

 dày

0.06

 sayı

0.06

-cal

0.06

 размер

0.06

 чемпіон

0.06

 bigger

0.06

 relying

0.06

ário

0.06

 persuade

0.06

Activations Density 0.016%

Date and time formatting

This neuron does not detect any pattern—it never activates for any token.

No Comments

No Known Activations

Date and time formatting

This neuron does not detect any pattern—it never activates for any token.

No Comments

No Known Activations