INDEX

Explanations

reviews and descriptions of food items and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

vron

-0.16

 sushi

-0.15

peq

-0.15

 Cuisine

-0.14

 culinary

-0.14

 cooking

-0.14

bate

-0.14

hoa

-0.14

Cook

-0.14

 baking

-0.14

POSITIVE LOGITS

 specials

0.22

 order

0.21

-order

0.19

 orders

0.18

order

0.18

 ordered

0.18

 ORDER

0.17

orders

0.17

 Order

0.17

ent

0.16

Activations Density 0.085%

reviews and descriptions of food items and dining experiences

No Comments

No Known Activations