INDEX

Explanations

instances of "hands-on" activities or experiences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð¾Ñĥ

-0.17

ailable

-0.16

Å¡ÃŃ

-0.15

.sponge

-0.15

htable

-0.14

cctor

-0.14

Å¡ak

-0.14

ilik

-0.14

alto

-0.14

adors

-0.14

POSITIVE LOGITS

-on

0.28

 dirty

0.27

-down

0.24

 Dirty

0.23

 hands

0.23

dirty

0.23

free

0.22

 down

0.22

-off

0.21

-free

0.21

Activations Density 0.007%

instances of "hands-on" activities or experiences

No Comments

No Known Activations