INDEX

Explanations

concepts and terminology related to programming entities, structures, and data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

as

-0.14

he

-0.14

æĴ

-0.14

his

-0.14

Arg

-0.14

we

-0.14

Mu

-0.13

Ch

-0.13

 standard

-0.13

POSITIVE LOGITS

uve

0.15

Ä±rak

0.14

antino

0.14

istol

0.14

jiÅ¡Å¥

0.14

 scÃ©

0.14

ê±´

0.14

inqu

0.13

arend

0.13

ÑĨÐµ

0.13

Activations Density 1.332%

concepts and terminology related to programming entities, structures, and data manipulation

No Comments

No Known Activations