INDEX

Explanations

Input

np_max-act · gemini-2.0-flash

This neuron activates on numeric literals (especially floating‐point constants and shape/size parameters) in code snippets.

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

 řed

-0.07

 (“

-0.06

UBLISH

-0.06

_seed

-0.06

^^

-0.06

 kurz

-0.06

landır

-0.06

POSITIVE LOGITS

 buiten

0.07

aux

0.06

 میلادی

0.06

="<?=$

0.06

ılı

0.06

(my

0.06

افت

0.06

ические

0.06

 outdoor

0.06

 remodeling

0.06

Activations Density 0.002%

Input

This neuron activates on numeric literals (especially floating‐point constants and shape/size parameters) in code snippets.

No Comments

No Known Activations

Input

This neuron activates on numeric literals (especially floating‐point constants and shape/size parameters) in code snippets.

No Comments

No Known Activations