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

alary

-0.15

 çĤ

-0.15

 Nose

-0.15

 ç·

-0.14

ungan

-0.14

 Maul

-0.14

apesh

-0.14

 Fallon

-0.14

 typealias

-0.13

Muon

-0.13

POSITIVE LOGITS

HasBeenSet

0.36

Aws

0.31

 Amazon

0.30

Aws

0.28

AWS

0.26

Amazon

0.26

aws

0.24

 amazon

0.24

AW

0.20

amazon

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.