INDEX

Explanations

symbols or characters indicating specific data or code structures

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

Ãĥ

-0.15

ÃĤ

-0.15

 Moff

-0.15

 Dodd

-0.14

 Ð¿ÑĢÐµÐ´ÐµÐ»

-0.14

 ÃĤ

-0.14

 ï¿½

-0.14

 Jarvis

-0.13

 Sanford

-0.13

irsch

-0.13

POSITIVE LOGITS

 Hungarian

0.39

 Hungary

0.35

Hung

0.31

 Budapest

0.29

 Hung

0.28

.hu

0.28

 VÃ¡c

0.24

Sz

0.23

 Slovak

0.23

Sz

0.21

Activations Density 0.001%

symbols or characters indicating specific data or code structures

No Comments

No Known Activations