INDEX

Explanations

relationships and conflicts involving family dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

avis

-0.15

ÐµÐ´Ð°Ð³

-0.14

ãĥ³ãĥķ

-0.14

zag

-0.14

obic

-0.13

uggy

-0.13

oki

-0.13

antis

-0.13

Å¡k

-0.13

arring

-0.13

POSITIVE LOGITS

 ÑĤÐ¾Ð¶Ðµ

0.68

 also

0.64

too

0.63

also

0.54

too

0.54

 ebenfalls

0.51

 ocksÃ¥

0.50

 ALSO

0.49

 Ã©galement

0.49

ä¹Łæĺ¯

0.48

Activations Density 1.189%

relationships and conflicts involving family dynamics

No Comments

No Known Activations