INDEX

Explanations

references to scientific datasets and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Mans

-0.16

thon

-0.15

 corpor

-0.15

doc

-0.15

 Grove

-0.14

pdf

-0.14

gen

-0.14

cod

-0.14

POSITIVE LOGITS

elah

0.15

 VerfÃ¼g

0.15

uko

0.15

 éĬ

0.15

ply

0.14

.gdx

0.14

 Dialog

0.14

ypse

0.14

esti

0.14

ÐºÐ°Ð¿

0.14

Activations Density 0.044%

references to scientific datasets and their characteristics

No Comments

No Known Activations