INDEX

Explanations

descriptive language related to food and culinary experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 garlic

-0.19

 seasoning

-0.18

 chili

-0.18

 peppers

-0.18

 Garlic

-0.18

 pepper

-0.18

ABEL

-0.17

hani

-0.16

 oils

-0.16

 chips

-0.15

POSITIVE LOGITS

 cust

0.31

 dessert

0.28

cust

0.27

 Cust

0.27

 sponge

0.26

 desserts

0.24

 parfait

0.23

 pudding

0.23

 Dess

0.23

dess

0.22

Activations Density 0.061%

descriptive language related to food and culinary experiences

No Comments

No Known Activations