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

_Ptr

-0.15

ÑĢÑĥÐ·

-0.13

imson

-0.13

éĿĴå¹´

-0.13

lon

-0.13

 Unsure

-0.13

 Illustrator

-0.12

 Leer

-0.12

 ØµÙĨ

-0.12

Jeg

-0.12

POSITIVE LOGITS

 maid

0.21

 Human

0.20

 slavery

0.19

ma

0.19

 human

0.19

 slave

0.19

 Slave

0.19

 servant

0.18

 employer

0.18

 employee

0.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.