INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ĮĢ

-0.16

inned

-0.14

leaf

-0.14

 sorts

-0.14

.bp

-0.14

ä½µ

-0.14

ling

-0.13

Äįe

-0.13

 WWII

-0.13

[_

-0.13

POSITIVE LOGITS

kowski

0.17

apia

0.16

rah

0.15

0.14

 Networking

0.14

 Wall

0.14

 conference

0.14

UPPORTED

0.14

 conferences

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.