INDEX

Explanations

Numbers

np_max-act · gemini-2.0-flash

This neuron responds to floating-point numeric literals (i.e. numbers containing a decimal point) in the code.

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

ंक

-0.07

brids

-0.07

 autobiography

-0.07

gun

-0.07

บอก

-0.07

 Avery

-0.07

-0.06

 Discussion

-0.06

-associated

-0.06

.Anchor

-0.06

POSITIVE LOGITS

�

0.07

 scop

0.07

DESC

0.06

 zast

0.06

mez

0.06

 ดาว

0.06

 Moines

0.06

 vede

0.06

 Perm

0.06

اهش

0.06

Activations Density 0.157%

Numbers

This neuron responds to floating-point numeric literals (i.e. numbers containing a decimal point) in the code.

No Comments

No Known Activations