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

acements

-0.15

elyn

-0.15

assin

-0.15

Î±Ïĥ

-0.14

ghan

-0.14

ewood

-0.14

okud

-0.14

 ÑģÐ¸ÑĢ

-0.14

åĢĻ

-0.14

askell

-0.13

POSITIVE LOGITS

uli

0.16

ocoa

0.14

.converter

0.14

ahy

0.14

ConfigurationException

0.14

é²

0.14

uly

0.14

iej

0.14

eve

0.13

 Trojan

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.