INDEX

Explanations

references to case studies and examples in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Watts

-0.15

deniz

-0.14

 Baldwin

-0.14

/packages

-0.14

Å©

-0.13

cr

-0.13

åħ¥ãĤĮ

-0.13

 Malk

-0.13

ictor

-0.13

 hollow

-0.13

POSITIVE LOGITS

 konkrÃ©t

0.18

_cases

0.17

 Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.17

ovu

0.16

 cases

0.16

 Cases

0.16

Cases

0.15

ohon

0.15

ä¾ĭ

0.15

Activations Density 0.109%

references to case studies and examples in research contexts

No Comments

No Known Activations