INDEX

Explanations

question marks

np_max-act · gemini-2.0-flash

Detects conversation/turn boundaries (the end-of-text/end-of-turn marker and sentence-final/question boundaries in user utterances).

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

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 frem

-0.07

%'

-0.07

 люб

-0.07

�

-0.07

歌

-0.06

uğ

-0.06

 pepp

-0.06

üç

-0.06

TER

-0.06

reck

-0.06

POSITIVE LOGITS

 усіх

0.06

 bombs

0.06

및

0.06

 الولايات

0.06

 turno

0.06

 ضربه

0.06

 conceive

0.06

 onUpdate

0.06

 Laos

0.06

овые

0.06

Activations Density 0.077%

question marks

Detects conversation/turn boundaries (the end-of-text/end-of-turn marker and sentence-final/question boundaries in user utterances).

No Comments

No Known Activations