INDEX

Explanations

call

np_max-act · gemini-2.0-flash

The neuron fires on text describing calling one function from another and forwarding its arguments—especially the use of “*args” unpacking in function calls.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

discussing the use of arguments and keyword arguments in Python functions.

oai_token-act-pair · gpt-4o-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

tracted

-0.07

Sta

-0.07

iationException

-0.07

Tut

-0.06

 Higgins

-0.06

CPP

-0.06

 سل

-0.06

 Бер

-0.06

symbols

-0.06

Bal

-0.06

POSITIVE LOGITS

 εί

0.07

 ऑनल

0.07

 中国

0.06

 goede

0.06

 Flex

0.06

>Total

0.06

 SHOULD

0.06

änder

0.06

 moż

0.06

 абсолют

0.06

Activations Density 0.023%

call

The neuron fires on text describing calling one function from another and forwarding its arguments—especially the use of “*args” unpacking in function calls.

discussing the use of arguments and keyword arguments in Python functions.

No Comments

No Known Activations