INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 SOLD

-0.16

olicit

-0.15

ÐµÑĢÐ±

-0.15

agos

-0.15

fug

-0.14

elian

-0.14

INCT

-0.14

thren

-0.14

uese

-0.14

ibus

-0.14

POSITIVE LOGITS

orro

0.16

ļĮ

0.14

 Revenge

0.14

lich

0.13

 hrad

0.13

orre

0.13

boards

0.13

ende

0.13

 eher

0.13

 tÃ¬nh

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.