INDEX

Explanations

references to changes over time and advancements in technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

olumn

-0.17

à¸£à¸Ķ

-0.16

anki

-0.15

herit

-0.14

irsch

-0.14

histor

-0.14

omba

-0.14

edia

-0.14

 heritage

-0.13

á»±c

-0.13

POSITIVE LOGITS

 intervening

0.25

 changed

0.24

 change

0.22

changed

0.21

 changes

0.20

change

0.19

 Changed

0.19

åıĺåĮĸ

0.19

chang

0.18

-change

0.18

Activations Density 0.110%

references to changes over time and advancements in technology

No Comments

No Known Activations