INDEX

Explanations

coax

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the technical term “coaxial” (often split into “coax” + “ial”).

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

 fronts

-0.07

 بپ

-0.07

.lower

-0.07

_FIRE

-0.07

 많은

-0.07

 cấp

-0.06

せて

-0.06

%.↵↵

-0.06

 dumps

-0.06

POSITIVE LOGITS

 coax

0.12

Thông

0.07

zag

0.07

:focus

0.07

xc

0.07

ijkstra

0.06

 Conv

0.06

JSON

0.06

Organization

0.06

 desenv

0.06

Activations Density 0.001%

coax

This neuron detects occurrences of the technical term “coaxial” (often split into “coax” + “ial”).

No Comments

No Known Activations