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

agged

-0.19

ag

-0.17

innen

-0.15

ı

-0.14

 perf

-0.14

rak

-0.14

\↵

-0.14

edio

-0.14

âĢ

-0.14

æĬĺ

-0.14

POSITIVE LOGITS

ÐĬ

0.15

.fig

0.15

AFX

0.14

mae

0.14

eniable

0.14

_refl

0.14

Î»Î¿Î¹

0.14

imbus

0.14

REFIX

0.14

ackers

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.