INDEX

Explanations

orable

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the “Ignorable” attribute (e.g. mc:Ignorable) in XAML/XML markup.

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

dotenv

-0.07

.registration

-0.07

 produces

-0.06

成绩

-0.06

-es

-0.06

utterstock

-0.06

 printing

-0.06

 WebClient

-0.06

 expelled

-0.06

 bees

-0.06

POSITIVE LOGITS

['/

0.07

0.06

ionální

0.06

 dile

0.06

 possibile

0.06

PCB

0.06

"+

0.06

 leakage

0.06

šem

0.06

募

0.06

Activations Density 0.000%

orable

The neuron activates on occurrences of the “Ignorable” attribute (e.g. mc:Ignorable) in XAML/XML markup.

No Comments

No Known Activations