INDEX

Explanations

references to food-related experiences and promotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

xCD

-0.15

Cook

-0.14

recipes

-0.14

 cuis

-0.14

 Recipes

-0.14

.opend

-0.14

ÑĢÐ°Ð²Ð¸

-0.14

 cooking

-0.14

å¥´

-0.13

 recipes

-0.13

POSITIVE LOGITS

 wings

0.22

 Wings

0.18

 entr

0.18

 Caesar

0.18

ent

0.18

 specials

0.18

 combo

0.17

-order

0.17

 Combo

0.17

 fries

0.17

Activations Density 0.107%

references to food-related experiences and promotions

No Comments

No Known Activations