INDEX

Explanations

code syntax

np_max-act · gemini-2.0-flash

This neuron specializes in spotting bits of code markup—particularly HTML (or XML/Angular) tags and angle-bracketed elements.

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

设施

-0.07

igDecimal

-0.06

 prayer

-0.06

멀

-0.06

usaha

-0.06

_Equals

-0.06

gd

-0.06

Rh

-0.06

ขนาด

-0.06

 теат

-0.06

POSITIVE LOGITS

 acknowled

0.06

"This

0.06

 بان

0.06

ilateral

0.06

 optimize

0.06

pix

0.06

UID

0.06

ominated

0.06

WEB

0.06

Nov

0.06

Activations Density 0.112%

code syntax

This neuron specializes in spotting bits of code markup—particularly HTML (or XML/Angular) tags and angle-bracketed elements.

No Comments

No Known Activations

code syntax

This neuron specializes in spotting bits of code markup—particularly HTML (or XML/Angular) tags and angle-bracketed elements.

No Comments

No Known Activations