INDEX

Explanations

technical language related to performance protocols and node communication in computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.opensource

-0.16

rone

-0.15

arte

-0.15

 Bain

-0.14

ifestyle

-0.14

strain

-0.14

dee

-0.13

allback

-0.13

voc

-0.13

byn

-0.13

POSITIVE LOGITS

 upper

0.25

 bounds

0.24

 bound

0.23

 Upper

0.22

 amort

0.22

Upper

0.21

 worst

0.21

 Rounds

0.21

 oblivious

0.21

 rounds

0.20

Activations Density 0.073%

technical language related to performance protocols and node communication in computing

No Comments

No Known Activations