INDEX

Explanations

references to products and their specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 iPhones

-0.15

Ã¸j

-0.15

IPA

-0.15

Î¼Î¿

-0.15

 telephone

-0.15

 Morse

-0.14

éĽ»è©±

-0.14

Ìĥ

-0.14

telephone

-0.14

 Telephone

-0.14

POSITIVE LOGITS

 notebook

0.38

 notebooks

0.37

 Notebook

0.36

 laptop

0.33

 laptops

0.32

 Laptop

0.30

 Ultr

0.29

 Acer

0.28

 ultr

0.27

 convertible

0.27

Activations Density 0.031%

references to products and their specifications

No Comments

No Known Activations

references to products and their specifications

No Comments

No Known Activations