INDEX

Explanations

app

np_max-act · gemini-2.0-flash

This neuron activates on parts of web addresses, especially URL path segments and domain substrings.

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

.tt

-0.06

 меж

-0.06

olley

-0.06

wire

-0.06

 Только

-0.06

 chan

-0.06

 recuper

-0.06

inp

-0.06

 mich

-0.06

atile

-0.06

POSITIVE LOGITS

Mvc

0.07

ισμ

0.07

Aws

0.07

 tearDown

0.07

others

0.06

nl

0.06

 OWNER

0.06

 ApplicationException

0.06

 brilliantly

0.06

法律

0.06

Activations Density 0.008%

app

This neuron activates on parts of web addresses, especially URL path segments and domain substrings.

No Comments

No Known Activations