INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ERY

-0.17

 beyond

-0.16

ergic

-0.14

reu

-0.14

eryl

-0.14

esson

-0.14

 past

-0.13

 positional

-0.13

ery

-0.13

POSITIVE LOGITS

åĪ·

0.15

 Plains

0.15

ght

0.14

abouts

0.14

zza

0.14

iors

0.14

äºī

0.13

pik

0.13

ark

0.13

UIApplication

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.