INDEX

Explanations

references to authors and their works, particularly those involved in book publishing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.15

etat

-0.14

actor

-0.14

ESP

-0.14

partment

-0.14

 storefront

-0.14

aqu

-0.14

asher

-0.14

apt

-0.14

errat

-0.13

POSITIVE LOGITS

 novel

0.21

 author

0.17

 onBind

0.16

 autor

0.15

 Author

0.15

dab

0.14

itudes

0.14

ycastle

0.14

Writes

0.14

ado

0.14

Activations Density 0.208%

references to authors and their works, particularly those involved in book publishing

No Comments

No Known Activations