INDEX

Explanations

-dismiss

np_max-act · gemini-2.0-flash

The neuron activates on “data-dismiss” attributes in HTML elements (i.e. the tokens of the form data-dismiss).

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

meniz

-0.08

یه

-0.07

Sunday

-0.06

OX

-0.06

criptors

-0.06

astered

-0.06

 چهار

-0.06

nih

-0.06

-seeking

-0.06

IA

-0.06

POSITIVE LOGITS

-dismiss

0.08

0.07

，与

0.06

 Cosmic

0.06

 غذ

0.06

 falls

0.06

-output

0.06

 passports

0.06

领导

0.06

elle

0.06

Activations Density 0.001%

-dismiss

The neuron activates on “data-dismiss” attributes in HTML elements (i.e. the tokens of the form data-dismiss).

No Comments

No Known Activations