INDEX

Explanations

mathematical terms and notation involving equations and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

wake

-0.16

zet

-0.15

éĢĨ

-0.15

roat

-0.14

ecta

-0.14

mÃŃt

-0.14

actory

-0.13

à¹ģà¸£à¸ģ

-0.13

ÃŃÅ¾

-0.13

HR

-0.13

POSITIVE LOGITS

Â²

0.32

 squared

0.31

Squared

0.31

0.30

0.29

 squares

0.27

'^

0.26

"^

0.25

Squ

0.25

_squared

0.25

Activations Density 0.082%

mathematical terms and notation involving equations and variables

No Comments

No Known Activations