INDEX

Explanations

technical terms and instructions related to multimedia production

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

ABCDEFG

-0.15

åĦ

-0.14

orsch

-0.14

ubs

-0.14

irim

-0.14

alli

-0.13

.zh

-0.13

isay

-0.13

/browse

-0.13

Î»Î»Î±

-0.13

POSITIVE LOGITS

 Pathfinder

0.19

 guides

0.18

jong

0.18

 Duplicate

0.16

 Guides

0.16

 duplicated

0.16

 Transparency

0.16

 Stroke

0.16

CMD

0.16

Duplicate

0.15

Activations Density 0.007%

technical terms and instructions related to multimedia production

No Comments

No Known Activations