INDEX

Explanations

references to series and books

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

onet

-0.16

ARI

-0.14

ope

-0.14

etal

-0.14

rollable

-0.14

elian

-0.14

asti

-0.14

ceptar

-0.14

POSITIVE LOGITS

-series

0.17

Ãºp

0.16

-Series

0.15

Series

0.15

Ã¼f

0.15

uft

0.14

 series

0.14

unsubscribe

0.14

Fant

0.14

 Series

0.14

Activations Density 0.024%

references to series and books

No Comments

No Known Activations