INDEX

Explanations

references to software functionality and context menus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Montgomery

-0.16

ataire

-0.15

 Mort

-0.15

eler

-0.14

ampo

-0.14

 Morg

-0.14

ÏīÎ¼Î±

-0.14

iaz

-0.14

 Martial

-0.14

Î±ÏģÎ±

-0.14

POSITIVE LOGITS

 menu

0.99

 Menu

0.90

 menus

0.87

menu

0.86

Menu

0.82

_menu

0.80

-menu

0.80

men

0.80

Men

0.77

.menu

0.76

Activations Density 0.089%

references to software functionality and context menus

No Comments

No Known Activations