INDEX

Explanations

questions that start with "which."

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

idan

-0.19

adium

-0.15

Å¡tÄĽ

-0.14

iid

-0.14

sd

-0.14

 Handling

-0.14

ialis

-0.14

 Crew

-0.14

crew

-0.14

POSITIVE LOGITS

ë¡Ŀ

0.16

anga

0.15

Fi

0.15

ÐºÐ¸Ð½

0.14

Fi

0.14

erv

0.14

fi

0.14

wyn

0.14

ÑĦÐµÐºÑĤÐ¸Ð²

0.14

Activations Density 0.022%

questions that start with "which."

No Comments

No Known Activations