INDEX

Explanations

specific geographic locations and institutions related to education and research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Budapest

-0.14

 Helsinki

-0.14

 Willi

-0.14

 Aberdeen

-0.14

ilit

-0.14

 Eisen

-0.13

imit

-0.13

uc

-0.13

aba

-0.13

POSITIVE LOGITS

 à¸Ľà¸£à¸°à¹Ģà¸Ĺà¸¨

0.40

USA

0.39

 England

0.38

 Italy

0.34

 Australia

0.34

 Germany

0.34

 Spain

0.33

UK

0.33

 Canada

0.32

 France

0.32

Activations Density 0.297%

specific geographic locations and institutions related to education and research

No Comments

No Known Activations