INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ifestyles

-0.16

.dds

-0.15

 Lust

-0.14

Ø±Ø²

-0.14

adÄ±r

-0.14

azing

-0.13

eydi

-0.13

zin

-0.13

ellas

-0.13

ooks

-0.13

POSITIVE LOGITS

LEE

0.15

erialize

0.15

 âĸĪ

0.15

htt

0.15

LEC

0.14

ochen

0.14

ela

0.14

bone

0.14

/=

0.14

lee

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.