INDEX

Explanations

comparative phrases indicating significant changes or impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 slightly

-0.15

imore

-0.14

 LESS

-0.14

 Geographic

-0.14

Ð»Ð¸Ð¼

-0.13

LESS

-0.13

 less

-0.13

 shortest

-0.13

oten

-0.13

ãĥĥãĤ·ãĥ¥

-0.13

POSITIVE LOGITS

 significant

0.69

significant

0.57

 major

0.54

 Significant

0.53

 substantial

0.51

 signific

0.45

 serious

0.42

major

0.42

 Ð·Ð½Ð°Ñĩ

0.41

 considerable

0.38

Activations Density 0.322%

comparative phrases indicating significant changes or impacts

No Comments

No Known Activations

comparative phrases indicating significant changes or impacts

No Comments

No Known Activations