INDEX

Explanations

phrases that describe various complex processes and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Î¬Îº

-0.16

uchi

-0.15

 Knox

-0.15

 Jelly

-0.14

ington

-0.14

EFA

-0.14

thy

-0.14

 Wake

-0.14

ule

-0.14

Ban

-0.13

POSITIVE LOGITS

ichick

0.17

ersiz

0.17

-process

0.15

íĸ

0.15

ery

0.15

skb

0.14

Ã¼z

0.14

:^

0.14

ë§Īëĭ¤

0.14

mÃ¼r

0.14

Activations Density 0.046%

phrases that describe various complex processes and their implications

No Comments

No Known Activations