INDEX

Explanations

references to travel experiences and destinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ä¸ĭè½½æ¬¡æķ°

-0.17

 Corn

-0.17

 Khal

-0.15

 æµĻæ±Ł

-0.15

 åįİ

-0.15

Kh

-0.14

 Kings

-0.14

ãĥ¯ãĤ¤ãĥĪ

-0.13

 å·´

-0.13

 è©ķä¾¡

-0.13

POSITIVE LOGITS

 Japan

0.54

 Japanese

0.50

Japan

0.48

 Tokyo

0.46

Japanese

0.45

 japan

0.44

 ÚĺØ§Ù¾

0.41

 Osaka

0.41

 japanese

0.39

 Kyoto

0.36

Activations Density 0.492%

references to travel experiences and destinations

No Comments

No Known Activations