INDEX

Explanations

references to professional backgrounds and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ibble

-0.17

tod

-0.15

sov

-0.15

 dÃ¼n

-0.14

maal

-0.14

otto

-0.14

lich

-0.14

ottie

-0.14

imer

-0.14

 Testament

-0.13

POSITIVE LOGITS

 since

0.42

 longer

0.38

since

0.35

 ever

0.31

 longest

0.30

 Longer

0.29

 Since

0.28

Since

0.28

 forever

0.26

ever

0.23

Activations Density 0.082%

references to professional backgrounds and experiences

No Comments

No Known Activations