INDEX

Explanations

his

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect floating‐point decimal numbers (tokens representing numeric values like 0.217, 0.345, etc.).

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

(+

-0.06

.d

-0.06

وي

-0.06

 attracting

-0.06

 blacklist

-0.06

 modest

-0.06

setTitle

-0.06

 whitelist

-0.06

 khoa

-0.06

친

-0.06

POSITIVE LOGITS

 leftover

0.07

/E

0.06

 DWORD

0.06

 حفظ

0.06

 midterm

0.06

’à

0.06

 Επ

0.06

	Item

0.06

 prominence

0.06

)value

0.06

Activations Density 0.134%

his

The main thing this neuron does is detect floating‐point decimal numbers (tokens representing numeric values like 0.217, 0.345, etc.).

No Comments

No Known Activations