INDEX

Explanations

0

np_max-act · gemini-2.0-flash

The neuron fires on numeric version strings (e.g. “1.0”) in XML/DOCTYPE headers, i.e. version declarations.

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

 Soon

-0.07

 pride

-0.06

RESET

-0.06

ACC

-0.06

 selfies

-0.06

 summary

-0.06

-times

-0.06

/
↵
↵

-0.06

THREAD

-0.06

 ویرایش

-0.06

POSITIVE LOGITS

'al

0.07

ographs

0.06

PLUS

0.06

νι

0.06

)&&

0.06

취

0.06

Named

0.06

 وكان

0.06

violent

0.06

hwnd

0.06

Activations Density 0.000%

0

The neuron fires on numeric version strings (e.g. “1.0”) in XML/DOCTYPE headers, i.e. version declarations.

No Comments

No Known Activations