INDEX

Explanations

configuration elements and component definitions in structured data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ephy

-0.16

reich

-0.15

ez

-0.15

ÑĩÐ°ÑĤ

-0.14

 Bass

-0.13

ordion

-0.13

rip

-0.13

.shared

-0.13

iffs

-0.13

moc

-0.13

POSITIVE LOGITS

á»ĵi

0.16

 bÃ½

0.16

.easing

0.16

itet

0.15

ÑĢÐµÐ´Ð¸ÑĤ

0.15

rown

0.15

.rar

0.14

ì³

0.14

missible

0.14

 Alic

0.14

Activations Density 0.503%

configuration elements and component definitions in structured data

No Comments

No Known Activations