INDEX

Explanations

to

np_max-act · gemini-2.0-flash

The neuron specializes in detecting references to chemical exposure—especially words like “exposure,” “prolonged,” “vapors,” “dust,” and related terms.

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

-0.07

erno

-0.07

.code

-0.06

stringValue

-0.06

olarity

-0.06

 mắt

-0.06

 kodu

-0.06

 професси

-0.06

ूह

-0.06

 holidays

-0.06

POSITIVE LOGITS

 Auto

0.07

erh

0.06

REM

0.06

ブロ

0.06

 bard

0.06

aug

0.06

$MESS

0.06

unteers

0.06

 있으며

0.06

 Exhib

0.06

Activations Density 0.015%

to

The neuron specializes in detecting references to chemical exposure—especially words like “exposure,” “prolonged,” “vapors,” “dust,” and related terms.

No Comments

No Known Activations