INDEX

Explanations

instructions or suggestions related to cooking and food preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

exo

-0.15

 organic

-0.14

 LÃ¢m

-0.14

buz

-0.14

urgeon

-0.14

luv

-0.14

 èĳ

-0.14

 Dann

-0.14

-chevron

-0.13

keywords

-0.13

POSITIVE LOGITS

 stir

0.24

sou

0.23

 sauces

0.20

 Stir

0.20

 marin

0.19

 dress

0.18

 stirred

0.18

 salads

0.17

 dishes

0.17

 Stocks

0.17

Activations Density 0.060%

instructions or suggestions related to cooking and food preparation

No Comments

No Known Activations