INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ertz

-0.16

æŃ

-0.16

ÙĬÙĨÙĬØ©

-0.15

atoria

-0.15

onical

-0.15

itoris

-0.14

AspectRatio

-0.14

 Weiner

-0.13

 trace

-0.13

vÃŃ

-0.13

POSITIVE LOGITS

weeney

0.16

_EXPORT

0.14

allows

0.14

å¡

0.14

ois

0.14

ammo

0.14

 ÑĢÐ°

0.13

 Vocabulary

0.13

clinic

0.13

urations

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.