INDEX

Explanations

elements that indicate pagination, headings, and author information in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ledo

-0.16

Ã©nÃ©

-0.15

van

-0.15

olid

-0.15

ennie

-0.14

ë¥´

-0.14

iel

-0.14

Î¬Ïĥ

-0.14

.Host

-0.14

MAND

-0.14

POSITIVE LOGITS

sled

0.18

edor

0.15

/compiler

0.15

adil

0.15

orang

0.14

éłģ

0.14

FileVersion

0.14

cover

0.14

Ħĸ

0.14

rega

0.14

Activations Density 0.053%

elements that indicate pagination, headings, and author information in a document

No Comments

No Known Activations