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

 organisers

-0.14

 organisations

-0.14

 ðŁ

-0.14

cai

-0.14

aniel

-0.14

trak

-0.13

 Modular

-0.13

 modulo

-0.13

 Furn

-0.13

 organis

-0.13

POSITIVE LOGITS

 Mich

0.32

Mich

0.25

agr

0.22

Ag

0.22

 Michigan

0.21

ag

0.21

Fa

0.21

 Micha

0.19

Fa

0.19

 mich

0.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.