INDEX

Explanations

references to Greek language or terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÏİÎ½ÏĦÎ±ÏĤ

-0.15

 BÄ°L

-0.15

buc

-0.15

ç«¯

-0.15

Ð¼Ñĥ

-0.15

ture

-0.14

ngu

-0.14

ruz

-0.14

tah

-0.14

nick

-0.14

POSITIVE LOGITS

ton

0.21

 tÃ´n

0.20

 Paid

0.20

 autos

0.20

Äĵ

0.20

 pros

0.19

Kai

0.19

autos

0.19

kat

0.18

 paid

0.18

Activations Density 0.019%

references to Greek language or terms

No Comments

No Known Activations