INDEX

Explanations

water

np_max-act · gemini-2.0-flash

The neuron activates whenever the document mentions “water.”

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

崎

-0.06

 buzzing

-0.06

']}}</

-0.06

Yol

-0.06

 Narc

-0.06

claimer

-0.06

eming

-0.06

 Occup

-0.06

िख

-0.06

POSITIVE LOGITS

sno

0.07

ice

0.06

 associate

0.06

 griev

0.06

 demanded

0.06

TRY

0.06

,’

0.06

 Pharma

0.06

 synt

0.06

 accomplished

0.06

Activations Density 0.008%

water

The neuron activates whenever the document mentions “water.”

No Comments

No Known Activations