INDEX

Explanations

references to cakes and baking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Soup

-0.18

 chili

-0.18

 soup

-0.18

soup

-0.17

 Soup

-0.16

_ENDPOINT

-0.16

 Chili

-0.15

ì¡±

-0.15

 Bent

-0.15

ettle

-0.14

POSITIVE LOGITS

 cake

0.35

 cakes

0.32

cake

0.31

 Cake

0.30

Cake

0.26

cakes

0.26

 cupcakes

0.26

 baker

0.25

 batter

0.24

 Baker

0.24

Activations Density 0.041%

references to cakes and baking

No Comments

No Known Activations