INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

#Region

-0.15

oucher

-0.15

åĳ

-0.15

ampp

-0.14

udd

-0.14

 coordin

-0.14

 Gesture

-0.14

tabpanel

-0.13

ectar

-0.13

POSITIVE LOGITS

eb

0.15

ogg

0.14

cion

0.14

 Synd

0.14

.SERVER

0.13

 survivors

0.13

Ã´ng

0.13

 firmy

0.13

 exposures

0.13

tings

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.