INDEX

Explanations

specific references to people and their interactions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

IDDEN

-0.15

raquo

-0.14

Ð»Ð°Ð³Ð¾Ð´

-0.14

ishi

-0.14

Textures

-0.13

Ã¶tt

-0.13

frage

-0.13

Segoe

-0.13

ocal

-0.13

.HTML

-0.13

POSITIVE LOGITS

 Credit

0.39

Credit

0.36

 Photo

0.36

Photo

0.34

 credit

0.34

 Â©

0.33

Â©

0.32

credit

0.31

 Credits

0.31

 photo

0.30

Activations Density 0.264%

specific references to people and their interactions in various contexts

No Comments

No Known Activations