INDEX

Explanations

phrases related to action requests and user engagement

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

ancode

-0.16

æºĢ

-0.14

:UIAlert

-0.14

ostel

-0.14

isu

-0.14

 annonces

-0.13

Ã¡o

-0.13

_exempt

-0.13

 Phones

-0.13

eref

-0.13

POSITIVE LOGITS

 Like

0.40

 LIKE

0.36

 liking

0.33

 like

0.33

Like

0.32

like

0.30

ret

0.30

 subscribe

0.29

 likes

0.29

 liked

0.29

Activations Density 0.122%

phrases related to action requests and user engagement

No Comments

No Known Activations