INDEX

Explanations

variations and differences in processes, systems, and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ã¨s

-0.15

-0.14

BIND

-0.14

itty

-0.14

Ð°Ð½ÑģÐ¸

-0.13

itto

-0.13

á»©ng

-0.13

heten

-0.13

anca

-0.13

uzzi

-0.13

POSITIVE LOGITS

 differently

0.60

 different

0.56

 differs

0.49

different

0.49

 differ

0.48

 diferente

0.46

ä¸įåĲĮçļĦ

0.45

 Different

0.44

 khÃ¡c

0.43

 differed

0.43

Activations Density 0.379%

variations and differences in processes, systems, and relationships

No Comments

No Known Activations