INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

@show

-0.15

Ãªs

-0.15

ussian

-0.15

arie

-0.15

elpers

-0.15

á»įng

-0.14

 Manson

-0.14

Symfony

-0.14

akis

-0.14

PasswordField

-0.13

POSITIVE LOGITS

ullet

0.16

 schle

0.15

cad

0.14

ë£¡

0.14

ule

0.14

VENT

0.14

 Lump

0.14

cad

0.14

ukan

0.13

Jad

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.