INDEX

Explanations

references to graphics processing units (GPUs) and related technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Wikispecies

-0.17

xito

-0.16

akedown

-0.15

ÙĨÚ¯

-0.15

adero

-0.15

apur

-0.15

ambi

-0.14

odie

-0.14

uan

-0.14

orex

-0.14

POSITIVE LOGITS

 equivalent

0.15

ember

0.14

praak

0.14

mat

0.14

 Unsupported

0.14

Î´ÏĮ

0.14

Ø²Ùĩ

0.13

ãĥĭãĤ¢

0.13

.semantic

0.13

forc

0.13

Activations Density 0.005%

references to graphics processing units (GPUs) and related technology

No Comments

No Known Activations