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

 Prayer

-0.15

Cah

-0.15

Ãºsqueda

-0.14

.um

-0.14

ardon

-0.14

 prayer

-0.14

_SYN

-0.13

éĸ

-0.13

SizeMode

-0.13

icros

-0.13

POSITIVE LOGITS

 paving

0.21

Da

0.20

 chapter

0.18

 paved

0.18

Da

0.18

éĵº

0.17

 pavement

0.17

 pave

0.17

 commentators

0.16

chapter

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.