INDEX

Explanations

references to academic institutions and research activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ikan

-0.18

Reward

-0.16

thed

-0.15

steller

-0.14

bine

-0.14

çĶŁãģį

-0.14

ivy

-0.14

riet

-0.14

weed

-0.14

 wheel

-0.13

POSITIVE LOGITS

ropol

0.15

-educated

0.14

/fontawesome

0.14

ÙĨØ¯ÛĮ

0.14

.edu

0.14

Ø§Ø¸

0.14

}elseif

0.14

 Ð¿Ð¾Ð³Ð»ÑıÐ´

0.14

Warnings

0.14

ald

0.13

Activations Density 0.458%

references to academic institutions and research activities

No Comments

No Known Activations