INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ayette

-0.16

ãĥĥãĥĦ

-0.15

cla

-0.15

.criteria

-0.15

CRY

-0.14

SetTitle

-0.14

UCKET

-0.14

'field

-0.14

cb

-0.14

vais

-0.14

POSITIVE LOGITS

 Canberra

0.25

Australian

0.23

 Australian

0.23

 Melbourne

0.22

 Australia

0.22

 Tasmania

0.22

Australia

0.21

 Queensland

0.21

 bush

0.19

 Barang

0.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.