INDEX

Explanations

how

np_max-act · gemini-2.0-flash

phrases that structure or qualify statements—especially negations, question framers, and other discourse markers indicating evaluation or explanation.

oai_token-act-pair · gpt-5 Triggered by @vetterc0

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

 gist

-0.07

ónico

-0.07

 teasing

-0.06

MC

-0.06

 Tecn

-0.06

nn

-0.06

 promoter

-0.06

-cn

-0.06

 servlet

-0.06

 chiefly

-0.06

POSITIVE LOGITS

OCI

0.06

 приобрет

0.06

FileNotFoundException

0.06

_attempt

0.06

 dangerously

0.06

々

0.06

шин

0.06

 humanity

0.06

$"{

0.06

Ownership

0.06

Activations Density 0.221%

how

phrases that structure or qualify statements—especially negations, question framers, and other discourse markers indicating evaluation or explanation.

No Comments

No Known Activations