INDEX

Explanations

programming-related terminology and constructs

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

 Narr

-0.17

 Perkins

-0.15

 Dale

-0.14

 norm

-0.14

 Vale

-0.14

Cav

-0.14

 Observer

-0.14

umar

-0.14

Biz

-0.14

POSITIVE LOGITS

 menu

0.55

 menus

0.53

 Menu

0.52

 MENU

0.49

Menu

0.48

menu

0.47

-menu

0.41

_menu

0.40

/menu

0.40

MENU

0.39

Activations Density 0.000%

programming-related terminology and constructs

No Comments

No Known Activations