INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

obby

-0.15

reed

-0.15

ulus

-0.15

lech

-0.15

 Celebration

-0.14

etre

-0.14

ì²ľ

-0.14

stor

-0.14

-0.13

arry

-0.13

POSITIVE LOGITS

dden

0.17

rama

0.17

 intellig

0.15

oden

0.15

 duplic

0.15

 uncont

0.15

zell

0.14

Zy

0.14

heid

0.14

 catholic

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.