INDEX

Explanations

references to liability and disclaimers regarding information or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

itech

-0.17

 KrÃ¡l

-0.15

datable

-0.14

abbo

-0.14

lice

-0.14

íĻ©

-0.13

 DÄĽ

-0.13

 Pierce

-0.13

ierce

-0.13

 Undefined

-0.13

POSITIVE LOGITS

elm

0.17

ptions

0.15

stal

0.15

Anywhere

0.14

Stencil

0.14

Ank

0.14

eydi

0.14

çİĽ

0.14

ãģĶãģĸ

0.14

Ð¸ÑģÑĮ

0.14

Activations Density 0.019%

references to liability and disclaimers regarding information or services

No Comments

No Known Activations