INDEX

Explanations

phrases related to learning processes and advice on managing challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ushman

-0.16

á»ĩ

-0.16

Ãª

-0.16

ady

-0.16

uka

-0.15

ole

-0.15

 Watt

-0.15

à¸«à¸Ļ

-0.14

McN

-0.14

è£ģ

-0.14

POSITIVE LOGITS

 myself

0.25

æĺ¯æĪĳ

0.21

my

0.20

æĪĳçļĦ

0.20

 minha

0.19

 tÃ´i

0.18

 meinem

0.16

è®©æĪĳ

0.15

 meiner

0.15

æĪĳ

0.15

Activations Density 0.230%

phrases related to learning processes and advice on managing challenges

No Comments

No Known Activations