INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

OLON

-0.18

 "\↵

-0.16

ÃŃl

-0.15

olon

-0.15

PÅĻÃŃ

-0.14

"..

-0.14

tsy

-0.14

 æ¶

-0.13

.flink

-0.13

 prostitut

-0.13

POSITIVE LOGITS

igham

0.19

 which

0.18

ahn

0.15

==>

0.15

0.14

 mass

0.14

muz

0.14

ousse

0.14

↵

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.