INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

pecially

-0.15

opus

-0.15

 Mong

-0.14

ties

-0.14

celik

-0.14

exampleModal

-0.14

iser

-0.14

éªĮ

-0.14

ured

-0.14

ries

-0.14

POSITIVE LOGITS

kill

0.19

age

0.16

uktur

0.15

geh

0.14

DDL

0.14

andle

0.14

 Shoe

0.14

ialis

0.14

-driving

0.13

haft

0.13

Activations Density 0.038%

No Comments

No Known Activations