INDEX

Explanations

amend

np_max-act · gemini-2.0-flash

This neuron detects mentions of amending or amendments to laws, policies, or formal documents.

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

ortality

-0.08

ระบบ

-0.07

bio

-0.07

_TRACK

-0.07

 srdce

-0.07

نتاج

-0.06

 tactical

-0.06

achine

-0.06

"\"

-0.06

 دوربین

-0.06

POSITIVE LOGITS

 amend

0.10

 amended

0.09

 amendment

0.09

 Amend

0.08

 enlarged

0.07

 beled

0.07

 Amanda

0.07

 amendments

0.07

0.06

Activations Density 0.005%

amend

This neuron detects mentions of amending or amendments to laws, policies, or formal documents.

No Comments

No Known Activations