INDEX

Explanations

geographic references and significant locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÃŃst

-0.18

Ã¤r

-0.17

Ã¦r

-0.17

Å¾en

-0.16

 kÃ¤

-0.16

ENAME

-0.16

ÅĤu

-0.16

ÃŃa

-0.16

Ã¡rio

-0.15

 GÃ¼n

-0.15

POSITIVE LOGITS

 Budapest

0.39

 Hungarian

0.37

 Hungary

0.36

Sz

0.34

Cs

0.33

Sz

0.31

Gy

0.30

Hung

0.30

.hu

0.28

Cs

0.27

Activations Density 0.065%

geographic references and significant locations

No Comments

No Known Activations