INDEX

Explanations

phrases related to eating and diet

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 coffee

-0.15

 Coffee

-0.15

 wines

-0.15

mlin

-0.14

atcher

-0.14

edics

-0.14

 Wine

-0.14

uz

-0.14

aks

-0.14

POSITIVE LOGITS

/dr

0.25

 disorders

0.23

 Disorders

0.20

 Disorder

0.19

 disorder

0.18

/shop

0.17

ery

0.17

vor

0.17

 habits

0.16

 humble

0.15

Activations Density 0.039%

phrases related to eating and diet

No Comments

No Known Activations