INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rouw

-0.16

ØªÙĦ

-0.15

eki

-0.14

reff

-0.14

hazi

-0.14

aan

-0.14

toFloat

-0.14

laz

-0.13

letcher

-0.13

loff

-0.13

POSITIVE LOGITS

 terr

0.16

 interp

0.15

antiago

0.15

core

0.14

izzo

0.14

é¡Į

0.14

irma

0.14

clair

0.14

epy

0.14

orio

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.