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

akit

-0.14

 cruiser

-0.14

 soft

-0.14

 Cruiser

-0.14

 shit

-0.14

 passive

-0.13

esel

-0.13

fuck

-0.13

/loose

-0.13

POSITIVE LOGITS

CO

0.19

 IPCC

0.19

USA

0.19

 Carbon

0.18

 carbon

0.17

carbon

0.16

 Gore

0.16

 fossil

0.16

CO

0.16

-job

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.