INDEX

Explanations

varied text snippets

np_max-act · gemini-2.0-flash

This neuron detects the company’s proper name or title—i.e. it activates on tokens that make up the business’s name.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fire

-0.06

FF

-0.06

'}

-0.06

(which

-0.06

/language

-0.06

antas

-0.06

 leng

-0.06

coop

-0.06

ccd

-0.06

 Legendary

-0.06

POSITIVE LOGITS

 Representatives

0.07

 accessible

0.07

 QSql

0.07

 либо

0.07

 soit

0.06

Và

0.06

NavigationView

0.06

 αρχ

0.06

 stronghold

0.06

GetProcAddress

0.06

Activations Density 0.027%

varied text snippets

This neuron detects the company’s proper name or title—i.e. it activates on tokens that make up the business’s name.

No Comments

No Known Activations