INDEX

Explanations

)

np_max-act · gemini-2.0-flash

The neuron responds to floating‐point numeric literals (decimal numbers) 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ién

-0.07

deadline

-0.06

 ihrem

-0.06

 WLAN

-0.06

\Eloquent

-0.06

_utilities

-0.06

 çerç

-0.06

Sou

-0.06

REP

-0.06

POSITIVE LOGITS

 collapsing

0.07

 prefixed

0.07

 ко

0.07

 pounded

0.06

.COMP

0.06

etter

0.06

 Political

0.06

コード

0.06

 istiyor

0.06

Activations Density 0.005%

)

The neuron responds to floating‐point numeric literals (decimal numbers) in the code.

No Comments

No Known Activations