INDEX

Explanations

references to food and cooking

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

 Baker

-0.17

 meisjes

-0.16

Cake

-0.15

lobal

-0.15

 Cake

-0.15

 cake

-0.15

cake

-0.15

 Bakery

-0.15

ulpt

-0.15

 bakery

-0.14

POSITIVE LOGITS

 soup

0.56

 Soup

0.51

soup

0.46

sou

0.45

 broth

0.44

Soup

0.44

Sou

0.39

oup

0.34

_soup

0.33

Sou

0.32

Activations Density 0.105%

references to food and cooking

No Comments

No Known Activations