INDEX

Explanations

comments and posts

np_max-act · gemini-2.0-flash

The neuron fires on brief enthusiastic praise or complimentary remarks (positive sentiment exclamations).

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

FLAG

-0.07

elerin

-0.06

_Tis

-0.06

Ct

-0.06

PointerException

-0.06

 características

-0.06

BitFields

-0.06

xCE

-0.06

��

-0.06

Impossible

-0.06

POSITIVE LOGITS

-inter

0.07

 assail

0.07

&:

0.06

SKIP

0.06

Verts

0.06

regexp

0.06

_DI

0.06

?\

0.06

 الأخ

0.06

 подк

0.06

Activations Density 0.071%

comments and posts

The neuron fires on brief enthusiastic praise or complimentary remarks (positive sentiment exclamations).

No Comments

No Known Activations