INDEX

Explanations

elements related to specifications and characteristics of systems or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ziel

-0.17

erner

-0.15

/xhtml

-0.15

 Cove

-0.15

 ìĤ¬ëŀĮìĿĢ

-0.14

ë¡ľëĬĶ

-0.14

 Newman

-0.14

 Fitness

-0.14

 FITNESS

-0.13

 Cres

-0.13

POSITIVE LOGITS

)ë¥¼

0.22

)ìĿĦ

0.19

ãĢįãĤĴ

0.18

ãĢĭçļĦ

0.17

ï¼īçļĦ

0.16

ideshow

0.15

.Networking

0.15

occo

0.15

phin

0.14

”çļĦ

0.14

Activations Density 0.032%

elements related to specifications and characteristics of systems or products

No Comments

No Known Activations