INDEX

Explanations

the

np_max-act · gemini-2.0-flash

The neuron activates on decimal‐formatted numbers (e.g. floating‐point statistics and measurements).

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

 unlawful

-0.07

↵

-0.07

 Already

-0.07

 computer

-0.07

 Unique

-0.07

comp

-0.06

(textBox

-0.06

"]["

-0.06

↵

-0.06

 evrop

-0.06

POSITIVE LOGITS

 PANEL

0.07

SCRIPTOR

0.07

@Module

0.06

 savedInstanceState

0.06

 metrů

0.06

_MENU

0.06

setBackground

0.06

Merit

0.06

白

0.06

Dest

0.06

Activations Density 0.039%

the

The neuron activates on decimal‐formatted numbers (e.g. floating‐point statistics and measurements).

No Comments

No Known Activations