INDEX

Explanations

nutritional information and health-related details about food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

indir

-0.17

OrFail

-0.16

ÙĪØŃ

-0.15

ongyang

-0.15

indle

-0.14

Ð±Ð°Ñĩ

-0.14

iÅ¾

-0.14

agos

-0.14

 Gore

-0.14

iropr

-0.14

POSITIVE LOGITS

fat

0.23

Fat

0.22

Nut

0.22

fat

0.22

 nutritional

0.21

 saturated

0.21

 grams

0.21

 nutrition

0.20

 Nutrition

0.20

Nut

0.20

Activations Density 0.003%

nutritional information and health-related details about food

No Comments

No Known Activations