INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

gis

-0.16

ezi

-0.16

elas

-0.15

stdexcept

-0.15

ohana

-0.15

erde

-0.14

lisi

-0.14

iset

-0.14

cela

-0.14

lamaz

-0.14

POSITIVE LOGITS

.KeyPress

0.17

 Waters

0.15

ango

0.15

.pm

0.14

aments

0.13

 Ø¨Ø±Ú¯

0.13

Ùĭ

0.13

à¤¸à¤²

0.13

 correspondent

0.13

ÃŃ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.