INDEX

Explanations

geographic locations or addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

prak

-0.18

isz

-0.14

ois

-0.14

ouz

-0.14

.newLine

-0.14

slash

-0.14

 ãĥĹãĥŃ

-0.14

sci

-0.14

 Tulsa

-0.13

/MIT

-0.13

POSITIVE LOGITS

Son

0.40

Son

0.33

 Marin

0.32

 Sebast

0.31

Pet

0.28

SON

0.27

son

0.27

 Russian

0.24

 Mend

0.24

Tib

0.23

Activations Density 0.013%

geographic locations or addresses

No Comments

No Known Activations