INDEX

Explanations

terms related to leadership and guidance

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

oust

-0.17

Regardless

-0.15

aran

-0.15

oustic

-0.14

aight

-0.14

raith

-0.14

lst

-0.14

pcl

-0.14

obao

-0.14

implify

-0.14

POSITIVE LOGITS

 thanks

0.26

 leading

0.22

 lead

0.21

thanks

0.21

 leads

0.20

 Thanks

0.20

Thanks

0.20

 mostly

0.19

leading

0.19

lead

0.19

Activations Density 0.017%

terms related to leadership and guidance

No Comments

No Known Activations