INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.15

aign

-0.15

 dÃ¢n

-0.14

mailer

-0.14

quez

-0.14

 Sharma

-0.14

ACHI

-0.13

(?:

-0.13

ÑĪÐºÐ¸

-0.13

aea

-0.13

POSITIVE LOGITS

qv

0.17

munition

0.15

anje

0.15

BAT

0.14

oping

0.14

ika

0.14

otu

0.14

 creampie

0.14

umper

0.13

ÏĥÏī

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.