INDEX

Explanations

terms related to nutrition and dietary effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

istingu

-0.16

ocha

-0.15

 æ³

-0.14

ienes

-0.14

arkan

-0.14

roj

-0.14

Bookmark

-0.14

 parachute

-0.14

ACA

-0.13

 ÑĩÐ°Ð¹

-0.13

POSITIVE LOGITS

 feed

0.37

 Feed

0.32

 feeds

0.30

 feeding

0.28

 diets

0.28

Feed

0.27

feed

0.27

-feed

0.27

fed

0.26

/feed

0.26

Activations Density 0.023%

terms related to nutrition and dietary effects

No Comments

No Known Activations