INDEX

Explanations

variations of the word "participate" and its derivatives

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

-0.18

 ninh

-0.16

zza

-0.16

deen

-0.14

ityEngine

-0.14

bug

-0.14

.Guna

-0.14

ë°Ģ

-0.14

zos

-0.13

.AutoScaleMode

-0.13

POSITIVE LOGITS

atory

0.28

ipation

0.23

les

0.23

ACTION

0.21

edia

0.20

actory

0.20

iple

0.19

ip

0.19

lesh

0.18

hip

0.18

Activations Density 0.005%

variations of the word "participate" and its derivatives

No Comments

No Known Activations