INDEX

Explanations

instances of humor and laughter

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

-0.17

adge

-0.16

aney

-0.16

-0.15

à¸±à¸Ķ

-0.14

uzey

-0.14

enaire

-0.14

illes

-0.14

-0.13

enie

-0.13

POSITIVE LOGITS

upro

0.24

stocks

0.22

ingly

0.20

stock

0.20

 hyster

0.19

 upro

0.19

ably

0.19

 hearty

0.18

cry

0.17

track

0.17

Activations Density 0.017%

instances of humor and laughter

No Comments

No Known Activations