INDEX

Explanations

-NLS

np_max-act · gemini-2.0-flash

This neuron detects the numeric markers in “//$NON-NLS-#” localization comments.

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

 denominator

-0.06

ěti

-0.06

щая

-0.06

 Anton

-0.06

(vec

-0.06

씨

-0.06

ková

-0.06

tablet

-0.06

 pertinent

-0.06

 petals

-0.06

POSITIVE LOGITS

ned

0.07

.MessageBox

0.07

 Comparison

0.06

-NLS

0.06

 interiors

0.06

urable

0.06

changer

0.06

 Integrated

0.06

mallow

0.06

 Disorder

0.06

Activations Density 0.000%

-NLS

This neuron detects the numeric markers in “//$NON-NLS-#” localization comments.

No Comments

No Known Activations