INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ombo

-0.17

ORMAT

-0.17

VERS

-0.14

olle

-0.14

umbo

-0.14

Defense

-0.13

olv

-0.13

rv

-0.13

çłĶ

-0.13

arker

-0.13

POSITIVE LOGITS

MC

0.32

MC

0.31

_MC

0.24

 stadium

0.24

 club

0.23

.mc

0.23

 Fans

0.23

Fan

0.22

 fans

0.22

mc

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.