INDEX

Explanations

phrases related to inclusivity and variety in offerings or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

empo

-0.16

ords

-0.16

æ»ħ

-0.15

 Äĳi

-0.14

ibu

-0.14

ijo

-0.14

ije

-0.14

viron

-0.13

atu

-0.13

alars

-0.13

POSITIVE LOGITS

 something

0.29

 Something

0.25

something

0.24

Something

0.24

 cater

0.22

 everyone

0.21

omething

0.20

 appeal

0.20

 Everyone

0.20

 Cater

0.20

Activations Density 0.168%

phrases related to inclusivity and variety in offerings or experiences

No Comments

No Known Activations