INDEX

Explanations

accuracy

np_max-act · gemini-2.0-flash

This neuron activates on decimal numeric values reporting measurement statistics (e.g., accuracy or precision values).

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

形

-0.07

 Yong

-0.07

VIDEO

-0.06

.real

-0.06

tag

-0.06

災

-0.06

-icons

-0.06

 میلی

-0.06

birth

-0.06

Muslim

-0.06

POSITIVE LOGITS

entlich

0.07

rac

0.07

 accuracy

0.07

ähr

0.07

 liked

0.07

SB

0.06

ΕΡ

0.06

 Accuracy

0.06

 hindsight

0.06

AC

0.06

Activations Density 0.008%

accuracy

This neuron activates on decimal numeric values reporting measurement statistics (e.g., accuracy or precision values).

No Comments

No Known Activations

accuracy

This neuron activates on decimal numeric values reporting measurement statistics (e.g., accuracy or precision values).

No Comments

No Known Activations