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

 Whilst

-0.17

 whilst

-0.17

Whilst

-0.16

APH

-0.15

ertools

-0.15

yntax

-0.15

ãĥ¬ãĥĵ

-0.15

pcodes

-0.15

prd

-0.15

nze

-0.14

POSITIVE LOGITS

 Crime

0.23

Crime

0.18

 Moscow

0.18

 Crimea

0.17

Der

0.16

anches

0.15

 Crimes

0.15

oy

0.15

 crime

0.14

Ky

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.