INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Pikachu

-0.15

">ÃĹ</

-0.14

ä¼ı

-0.14

aurus

-0.13

itaire

-0.13

grily

-0.13

.setViewport

-0.13

ÙİØª

-0.13

POSITIVE LOGITS

icha

0.14

iena

0.14

ìĤ°

0.14

 ultimately

0.14

 somehow

0.14

ething

0.14

 assorted

0.13

 interracial

0.13

 eventually

0.13

aminer

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.