INDEX

Explanations

)

np_max-act · gemini-2.0-flash

This neuron detects occurrences of parenthesis tokens ( “(” and “)” ) in the text.

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

 parc

-0.06

�

-0.06

icont

-0.06

 regained

-0.06

ACHE

-0.06

 somew

-0.06

ustomer

-0.06

галі

-0.06

 додатков

-0.06

 сім

-0.06

POSITIVE LOGITS

 deceived

0.07

.Imaging

0.07

 ferr

0.06

_filepath

0.06

�

0.06

 punto

0.06

型

0.06

-transfer

0.06

.Connect

0.06

$body

0.06

Activations Density 0.001%

)

This neuron detects occurrences of parenthesis tokens ( “(” and “)” ) in the text.

No Comments

No Known Activations