INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

roman

-0.17

.hwp

-0.14

clazz

-0.14

oÅ¾

-0.14

ä¹¦è®°

-0.14

aclass

-0.14

NavController

-0.13

leftright

-0.13

amura

-0.13

flater

-0.13

POSITIVE LOGITS

si

0.29

mi

0.27

Mi

0.24

arr

0.24

Si

0.24

pas

0.23

 cust

0.23

si

0.22

Si

0.21

arr

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.