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

 crypt

-0.15

utes

-0.14

tero

-0.14

ub

-0.14

le

-0.13

hee

-0.13

oub

-0.13

ãģĤãģ®

-0.13

inst

-0.13

zel

-0.13

POSITIVE LOGITS

undi

0.15

å®ľ

0.15

senal

0.14

ayah

0.14

opoulos

0.14

POWER

0.14

íĳ¸

0.14

agus

0.13

ãĥ¥

0.13

.usermodel

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.