INDEX

Explanations

references to Microsoft Office products and related issues

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

oggles

-0.17

 Gore

-0.15

byn

-0.15

ALTH

-0.15

 Hollow

-0.15

odos

-0.14

hlas

-0.14

ĩĮ

-0.14

dd

-0.14

icles

-0.14

POSITIVE LOGITS

 Office

0.32

Office

0.28

0.25

.Office

0.22

 Excel

0.22

 office

0.22

.office

0.22

 Word

0.21

 SharePoint

0.21

Gro

0.20

Activations Density 0.013%

references to Microsoft Office products and related issues

No Comments

No Known Activations