INDEX

Explanations

lock

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

 cosmetics

-0.07

 เส

-0.07

cassert

-0.07

 crem

-0.07

(BigInteger

-0.07

 surfing

-0.07

 gray

-0.07

 curr

-0.06

 sept

-0.06

 marzo

-0.06

POSITIVE LOGITS

 Lock

0.11

Lock

0.10

 lock

0.09

 locking

0.09

 Locked

0.09

 locked

0.08

LOCK

0.08

lock

0.07

 imprisonment

0.07

Latch

0.07

Activations Density 0.017%

lock

No Comments

No Known Activations

lock

No Comments

No Known Activations