INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

im

-0.15

 Schw

-0.14

imits

-0.14

anh

-0.14

isc

-0.14

ÙĪÙĬÙĥ

-0.14

Ped

-0.14

Ã¡le

-0.14

linkplain

-0.14

bcm

-0.14

POSITIVE LOGITS

sh

0.40

amed

0.21

enan

0.20

rou

0.18

udd

0.17

lfw

0.17

unning

0.17

SCR

0.16

ushing

0.16

aming

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.