INDEX

Explanations

Non-specific nouns

np_max-act · gemini-2.0-flash

This neuron detects general or hedge-language words and phrases (like “things,” “everything,” “typical,” “many,” “no agreement”) that signal broad, non-specific statements.

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

 communism

-0.07

 multiplayer

-0.07

 Lionel

-0.07

}

↵

-0.07

θλη

-0.07

}")
↵

-0.07

 उठ

-0.06

？」↵↵

-0.06

 lame

-0.06

Islam

-0.06

POSITIVE LOGITS

�

0.08

READY

0.06

�

0.06

Brush

0.06

 Treat

0.06

_lng

0.06

 Looking

0.06

 الملك

0.06

六

0.06

 Load

0.06

Activations Density 0.027%

Non-specific nouns

This neuron detects general or hedge-language words and phrases (like “things,” “everything,” “typical,” “many,” “no agreement”) that signal broad, non-specific statements.

No Comments

No Known Activations

Non-specific nouns

This neuron detects general or hedge-language words and phrases (like “things,” “everything,” “typical,” “many,” “no agreement”) that signal broad, non-specific statements.

No Comments

No Known Activations