INDEX

Explanations

expressions related to group activities and social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ilon

-0.14

olia

-0.14

rello

-0.14

 indul

-0.13

è£ı

-0.13

 ÙĨØ³

-0.13

vay

-0.13

ilde

-0.13

.SelectedItems

-0.13

Khi

-0.13

POSITIVE LOGITS

 everywhere

0.64

 Everywhere

0.44

 wherever

0.39

 ubiquitous

0.35

 every

0.31

every

0.29

 throughout

0.29

 ubiqu

0.29

 EVERY

0.28

 omnip

0.27

Activations Density 0.251%

expressions related to group activities and social interactions

No Comments

No Known Activations