INDEX

Explanations

posture

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 penetrate

-0.07

"";

-0.06

校

-0.06

 utiliser

-0.06

Rig

-0.06

UTC

-0.06

ISyntaxException

-0.06

 Mundo

-0.06

 cancellationToken

-0.06

POSITIVE LOGITS

Startup

0.07

（笑

0.06

 işaret

0.06

/boot

0.06

듯

0.06

 روابط

0.06

 Ник

0.06

ไฟล

0.06

 Supplementary

0.06

 iteration

0.06

Activations Density 0.096%

posture

No Comments

No Known Activations