INDEX

Explanations

references to chemical processes and reactions

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

amo

-0.17

Rav

-0.15

aurus

-0.14

 Rewards

-0.14

icit

-0.14

-valu

-0.13

 ëħ¹

-0.13

 Joker

-0.13

 createState

-0.13

 opak

-0.13

POSITIVE LOGITS

 abstraction

0.23

 elim

0.23

 attack

0.22

 mechan

0.21

 elect

0.21

hal

0.21

 nucle

0.21

 elimination

0.20

 reaction

0.20

 abstract

0.19

Activations Density 0.028%

references to chemical processes and reactions

No Comments

No Known Activations