INDEX

Explanations

structured data or forms

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

ðĿ

-0.17

.management

-0.15

<\/

-0.14

 /*#__

-0.14

ypi

-0.14

aken

-0.14

+#+

-0.14

POSITIVE LOGITS

 ................................

0.39

................................

0.38

........................

0.37

................

0.32

 ................

0.27

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

0.27

........

0.24

âĢ¦âĢ¦âĢ¦âĢ¦

0.22

 ........

0.21

âĢ¦âĢ¦

0.18

Activations Density 0.004%

structured data or forms

No Comments

No Known Activations