INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

åĥħ

-0.15

è´¥

-0.15

loff

-0.14

asia

-0.14

edy

-0.14

ilio

-0.14

ipay

-0.14

lam

-0.14

uetype

-0.13

ordinates

-0.13

POSITIVE LOGITS

tph

0.18

izen

0.16

 trains

0.16

 numbered

0.16

 North

0.15

 electr

0.15

 apart

0.15

 Coronavirus

0.15

 Coach

0.15

 someday

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.