INDEX

Explanations

numerical values and quantities

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

eken

-0.14

mÃŃ

-0.14

avez

-0.13

 undergo

-0.13

ÎĲ

-0.13

OST

-0.13

ÙĪØ¬

-0.13

GINE

-0.13

-meter

-0.13

ÏĢÎ»

-0.13

POSITIVE LOGITS

ish

0.35

something

0.32

 something

0.30

odd

0.28

-s

0.28

Something

0.26

ISH

0.25

odd

0.24

 Something

0.24

omething

0.22

Activations Density 0.169%

numerical values and quantities

No Comments

No Known Activations