INDEX

Explanations

references to programming concepts and details associated with assembly language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

onet

-0.15

CADE

-0.15

.localized

-0.14

rava

-0.14

 Drops

-0.14

posix

-0.14

Caj

-0.14

 POSIX

-0.14

 Baghd

-0.14

 taraf

-0.14

POSITIVE LOGITS

 bank

0.28

 banks

0.26

ROM

0.25

 BANK

0.25

ram

0.24

 Bank

0.24

 addressing

0.24

 address

0.23

 addresses

0.23

bank

0.23

Activations Density 0.021%

references to programming concepts and details associated with assembly language

No Comments

No Known Activations