INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ansi

-0.16

issance

-0.15

 super

-0.15

æĬĳ

-0.15

emann

-0.15

-0.14

redential

-0.14

adÄĽ

-0.14

obsolete

-0.14

_superuser

-0.14

POSITIVE LOGITS

ync

0.16

 hasNext

0.15

 Hardcore

0.15

axed

0.15

 Sokol

0.15

ureka

0.14

ble

0.14

OPLE

0.14

cker

0.14

eo

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.