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

ippy

-0.15

eldom

-0.15

uml

-0.15

nergy

-0.15

emme

-0.14

 notoriously

-0.14

 vÃ¥r

-0.14

íħĮ

-0.13

ecast

-0.13

@nate

-0.13

POSITIVE LOGITS

Whe

0.15

oring

0.15

chl

0.15

lant

0.14

 Went

0.14

nst

0.13

inan

0.13

 åį

0.13

 nouvel

0.13

 ActionType

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.