INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

emme

-0.17

UEST

-0.17

apur

-0.15

ãģ¾ãģĽ

-0.14

ague

-0.14

toolbox

-0.14

Ð»Ð°Ð³

-0.14

mlink

-0.13

andle

-0.13

PRETTY

-0.13

POSITIVE LOGITS

brero

0.14

 toler

0.14

chs

0.14

odom

0.13

axter

0.13

çļĦä¸Ģä¸ª

0.13

 recru

0.13

 Evrop

0.13

olec

0.13

ÙĦØ·

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.