INDEX

Explanations

elements related to programming and regular expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Craig

-0.16

 çŃ

-0.14

 Ahmet

-0.14

 spontaneous

-0.14

ãģ£ãģ¨

-0.14

omas

-0.14

Craig

-0.14

atore

-0.14

 Abdel

-0.14

é»

-0.13

POSITIVE LOGITS

\\

0.48

\\

0.42

"\\

0.41

("\\

0.41

'\\

0.39

}\\

0.39

:\\

0.38

]\\

0.36

('\\

0.36

\\.

0.35

Activations Density 0.031%

elements related to programming and regular expressions

No Comments

No Known Activations