INDEX

Explanations

keywords associated with logic and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ð¸Ð·Ð½ÐµÑģ

-0.16

undle

-0.16

ä¸įåĪ°

-0.15

Ã¦k

-0.15

istrovstvÃŃ

-0.15

 ÙħØ¹ÙĦ

-0.15

IAS

-0.14

itzer

-0.14

uzzi

-0.13

éĢģæĸĻ

-0.13

POSITIVE LOGITS

as

0.71

 ÐºÐ°Ðº

0.39

als

0.35

 ÙĥÙħØ§

0.34

 sebagai

0.28

as

0.27

 ÏīÏĤ

0.26

ä½ľä¸º

0.24

 jako

0.23

as

0.22

Activations Density 0.074%

keywords associated with logic and programming concepts

No Comments

No Known Activations