INDEX

Explanations

sections related to data and reports

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Vader

-0.15

ropa

-0.15

ahi

-0.14

å·»

-0.14

¢

-0.14

Ã¤ÃŁ

-0.14

ÎµÎ¯

-0.13

ÑįÐ¹

-0.13

ä¿

-0.13

gas

-0.13

POSITIVE LOGITS

 Consortium

0.16

.infinity

0.15

 Westbrook

0.15

ayo

0.15

 consort

0.14

ftime

0.14

 partner

0.14

 ÑĩÐ¸ÑģÐ»Ñĸ

0.14

ÑĩÐ¸Ñģ

0.13

immel

0.13

Activations Density 0.297%

sections related to data and reports

No Comments

No Known Activations