INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

empt

-0.15

ICLE

-0.15

alling

-0.14

ables

-0.14

IGIN

-0.14

egade

-0.14

antal

-0.14

etten

-0.14

aller

-0.13

ucer

-0.13

POSITIVE LOGITS

strup

0.19

/local

0.17

aney

0.16

BEST

0.16

iz

0.14

ÑıÐ²

0.14

ÑĤÐ¾ÑĦ

0.14

-Pacific

0.14

-local

0.14

vers

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.