INDEX

Explanations

references to food and beverage-related content

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

 foods

-0.30

 Foods

-0.29

 Food

-0.24

foods

-0.24

 meals

-0.23

 comida

-0.23

Food

-0.23

 FOOD

-0.23

 alimentos

-0.23

 cuisine

-0.22

POSITIVE LOGITS

 drink

0.39

 beverage

0.32

 Drink

0.31

 Beverage

0.31

 drinks

0.31

 beverages

0.30

 Bever

0.30

drink

0.29

Drink

0.27

 Drinks

0.26

Activations Density 0.082%

references to food and beverage-related content

No Comments

No Known Activations