INDEX

Explanations

as

np_max-act · gemini-2.0-flash

The neuron activates specifically on occurrences of the Python keyword “as.”

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

یده

-0.07

 того

-0.07

 winding

-0.06

.RowStyles

-0.06

 Knight

-0.06

 مسئله

-0.06

 Markt

-0.06

 khăn

-0.06

(_,

-0.06

직

-0.06

POSITIVE LOGITS

leurs

0.07

'options

0.07

stellar

0.07

.getResource

0.06

۲۰۱

0.06

ubes

0.06

ORIA

0.06

 informatie

0.06

FSIZE

0.06

 všechno

0.06

Activations Density 0.001%

as

The neuron activates specifically on occurrences of the Python keyword “as.”

No Comments

No Known Activations