INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

:CGRect

-0.17

ummings

-0.16

aeda

-0.15

gii

-0.15

rahim

-0.14

ctrine

-0.14

cheon

-0.14

bye

-0.14

utt

-0.14

lander

-0.14

POSITIVE LOGITS

our

0.18

ÏģÎ³

0.15

 Continent

0.14

rowse

0.14

angu

0.14

fer

0.14

ê°ģ

0.14

Our

0.14

redicate

0.14

Maz

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.