INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÐĽÐĺ

-0.15

.dm

-0.15

ialect

-0.14

plusplus

-0.14

 resultant

-0.14

ÐµÑĢÐº

-0.14

ROLS

-0.13

abase

-0.13

FACT

-0.13

ÐºÑĸÐ²

-0.13

POSITIVE LOGITS

errer

0.15

ogo

0.14

ftime

0.14

 Lion

0.14

ser

0.13

Î¬

0.13

rzy

0.13

oir

0.13

iras

0.13

boo

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.