INDEX

Explanations

:/

np_max-act · gemini-2.0-flash

This neuron detects filesystem path components (e.g. drive letters, slashes, and common directory names).

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

 Initially

-0.07

šel

-0.07

-get

-0.06

 cord

-0.06

confidence

-0.06

 định

-0.06

 bargain

-0.06

，没有

-0.06

่ว

-0.06

-com

-0.06

POSITIVE LOGITS

AU

0.07

/Typography

0.06

DDD

0.06

 دس

0.06

orphism

0.06

씨

0.06

<AudioSource

0.06

бом

0.06

.dtd

0.06

каж

0.06

Activations Density 0.011%

:/

This neuron detects filesystem path components (e.g. drive letters, slashes, and common directory names).

No Comments

No Known Activations