INDEX

Explanations

references to weight loss methods and dieting

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

ailer

-0.20

aina

-0.15

 Lung

-0.15

aeda

-0.14

Ð¾Ð²ÐµÑĢ

-0.14

letal

-0.14

reste

-0.14

 Yorker

-0.14

OLOR

-0.14

utenberg

-0.14

POSITIVE LOGITS

fat

0.43

Fat

0.35

fat

0.34

Fat

0.33

-fat

0.31

lip

0.29

FAT

0.29

 adip

0.28

 fatty

0.28

 contour

0.28

Activations Density 0.028%

references to weight loss methods and dieting

No Comments

No Known Activations

references to weight loss methods and dieting

No Comments

No Known Activations