INDEX

Explanations

recipes and cooking instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

raj

-0.15

lice

-0.14

 Quiz

-0.14

ilk

-0.13

Sac

-0.13

 é£

-0.13

 Mechan

-0.13

 slices

-0.13

roid

-0.13

POSITIVE LOGITS

 recipe

0.45

 recipes

0.41

recipe

0.35

 Recipe

0.33

 ÑĢÐµÑĨÐµÐ¿

0.30

 ÑĢÐµÑĨÐµÐ¿ÑĤ

0.30

 Recipes

0.29

Recipe

0.27

recipes

0.27

Recipes

0.26

Activations Density 0.139%

recipes and cooking instructions

No Comments

No Known Activations