INDEX

Explanations

<

np_max-act · gemini-2.0-flash

This neuron responds to XML/HTML–style markup elements, i.e. tokens involved in angle‐bracket tags.

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

 EXCEPTION

-0.07

Add

-0.07

 아이콘

-0.07

	Debug

-0.06

_BT

-0.06

_Reference

-0.06

ipop

-0.06

 silhouette

-0.06

 split

-0.06

ЮЛ

-0.06

POSITIVE LOGITS

 v�

0.06

�

0.06

Nobody

0.06

 resonate

0.06

 مان

0.06

rz

0.06

ffmpeg

0.05

 {})↵

0.05

Activations Density 0.003%

<

This neuron responds to XML/HTML–style markup elements, i.e. tokens involved in angle‐bracket tags.

No Comments

No Known Activations