INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

loquent

-0.16

-0.15

eza

-0.14

loh

-0.13

_ARG

-0.13

.openg

-0.13

uder

-0.13

POSITIVE LOGITS

anuts

0.15

allon

0.14

Ø³ØªØ§ÙĨ

0.14

/todo

0.14

vÄĽt

0.14

æ²¢

0.14

NamedQuery

0.14

Î¶Î¯

0.14

eted

0.14

GBP

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.