INDEX

Explanations

No Explanations Found

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

atel

-0.17

ubat

-0.16

icari

-0.15

esub

-0.15

 ÑħÐ¾Ð·ÑıÐ¹

-0.15

iferay

-0.14

 Craw

-0.14

NSS

-0.14

isle

-0.14

bid

-0.14

POSITIVE LOGITS

alt

0.23

 bulls

0.22

 pump

0.21

ETH

0.21

hod

0.20

 dump

0.20

 bears

0.19

ETH

0.19

 pumps

0.19

 bear

0.19

Activations Density 0.012%

No Comments

No Known Activations