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

hiba

-0.18

zas

-0.14

ă

-0.14

"""

-0.14

omid

-0.14

&apos

-0.13

lds

-0.13

"'

-0.13

.ld

-0.13

"!

-0.13

POSITIVE LOGITS

 Henry

0.32

Henry

0.28

hen

0.21

HEN

0.21

hen

0.20

HP

0.19

 Carol

0.19

 Miss

0.18

 Matt

0.18

HP

0.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.