INDEX

Explanations

terms related to solutions, performance, and development in a business context

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

edd

-0.17

Ã¢u

-0.16

 ÄĮer

-0.15

 Ø´ÙħØ§Ø±Ùĩ

-0.15

acket

-0.14

Ð¶ÐµÐ½

-0.14

UDO

-0.14

shaft

-0.13

phis

-0.13

 (*((

-0.13

POSITIVE LOGITS

 complement

0.20

 specific

0.19

hole

0.17

 compatible

0.16

hal

0.15

Specific

0.15

 compliment

0.15

Orth

0.15

Hal

0.15

ipro

0.15

Activations Density 0.011%

terms related to solutions, performance, and development in a business context

No Comments

No Known Activations