INDEX

Explanations

moon

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of moon phase terms (e.g., “full moon,” “new moon,” “waxing moon”).

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

Installer

-0.07

machine

-0.07

他們

-0.06

.code

-0.06

(thing

-0.06

 turbine

-0.06

 stationary

-0.06

Theta

-0.06

orent

-0.06

POSITIVE LOGITS

 servicing

0.07

从

0.06

 Zones

0.06

\%

0.06

ète

0.06

 communic

0.06

�

0.06

)section

0.06

 вий

0.06

τέ

0.06

Activations Density 0.003%

moon

The neuron activates on occurrences of moon phase terms (e.g., “full moon,” “new moon,” “waxing moon”).

No Comments

No Known Activations

moon

The neuron activates on occurrences of moon phase terms (e.g., “full moon,” “new moon,” “waxing moon”).

No Comments

No Known Activations