INDEX

Explanations

references to specific individuals or professionals related to social media and communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.18

--

-0.17

...

-0.16

 specialised

-0.14

...

-0.14

CRC

-0.14

....

-0.13

enta

-0.13

 Covent

-0.13

 -↵

-0.13

POSITIVE LOGITS

 Molly

0.27

 Book

0.27

Amy

0.23

Book

0.21

 Wilde

0.20

 Beer

0.19

 BOOK

0.19

 Party

0.19

(Book

0.18

Amy

0.18

Activations Density 0.003%

references to specific individuals or professionals related to social media and communication

No Comments

No Known Activations