INDEX

Explanations

scientific terms and references related to equations and mathematical theories

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

duk

-0.20

 Synd

-0.15

deen

-0.15

ozem

-0.15

ÑħÐ°

-0.14

èĲ½ãģ¡

-0.14

 races

-0.14

 zend

-0.14

 Britann

-0.14

 Shak

-0.14

POSITIVE LOGITS

 packing

0.24

 excluded

0.23

 hard

0.23

 hardcore

0.22

 Baxter

0.21

 pack

0.21

 collo

0.21

rep

0.20

jam

0.20

 pair

0.20

Activations Density 0.015%

scientific terms and references related to equations and mathematical theories

No Comments

No Known Activations