INDEX

Explanations

org

np_max-act · gemini-2.0-flash

comments and documentation related to software licensing and copyright information.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

This neuron activates on tokens forming the domain‐style prefixes in Java package and import statements (e.g. “org”, “com”, etc.).

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

ΜΑ

-0.07

 savvy

-0.06

upaten

-0.06

ρκεια

-0.06

したら

-0.06

ください

-0.06

ahat

-0.06

 فاصله

-0.06

意味

-0.06

POSITIVE LOGITS

_records

0.07

=os

0.06

oco

0.06

com

0.06

+h

0.06

execute

0.06

 rushes

0.06

ordon

0.06

art

0.06

 да

0.06

Activations Density 0.008%

org

comments and documentation related to software licensing and copyright information.

This neuron activates on tokens forming the domain‐style prefixes in Java package and import statements (e.g. “org”, “com”, etc.).

No Comments

No Known Activations