INDEX

Explanations

information

np_max-act · gemini-2.0-flash

The neuron flags semantically “content-heavy” words—key topic nouns and specialized terms rather than common function words.

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

Teacher

-0.07

 redhead

-0.06

WindowSize

-0.06

نتی

-0.06

 abrir

-0.06

лося

-0.06

(toolbar

-0.06

مار

-0.06

FileManager

-0.06

ใช

-0.06

POSITIVE LOGITS

 records

0.07

 uncommon

0.07

Pat

0.07

_way

0.07

 enqu

0.07

Rob

0.06

_na

0.06

 excessively

0.06

 prison

0.06

DET

0.06

Activations Density 0.627%

information

The neuron flags semantically “content-heavy” words—key topic nouns and specialized terms rather than common function words.

No Comments

No Known Activations

information

The neuron flags semantically “content-heavy” words—key topic nouns and specialized terms rather than common function words.

No Comments

No Known Activations