INDEX

Explanations

emphasis or excitement in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

éĤ£ç§į

-0.15

 navÃŃc

-0.15

 moreover

-0.14

.asp

-0.14

 cáº£

-0.14

>Main

-0.14

ataka

-0.14

 other

-0.13

åį´

-0.13

į°

-0.13

POSITIVE LOGITS

Hi

0.39

Hello

0.39

 Hello

0.39

Hi

0.38

 hello

0.35

hi

0.34

Greetings

0.32

hello

0.31

reetings

0.30

hi

0.29

Activations Density 0.346%

emphasis or excitement in statements

No Comments

No Known Activations