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

Ð°ÑĢÐ°Ð½

-0.17

Ð½Ð¾Ð¶

-0.17

iterals

-0.15

gui

-0.14

usra

-0.14

eyJ

-0.14

ojÃŃ

-0.14

 æľŁ

-0.14

Å¡lo

-0.14

ollar

-0.13

POSITIVE LOGITS

 Pres

0.23

Pres

0.20

cir

0.19

Cir

0.19

 Blanch

0.17

ifo

0.17

ca

0.17

Enum

0.16

son

0.16

Pvt

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.