INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

amespace

-0.18

æĹıèĩªæ²»

-0.17

Ã¦re

-0.15

aqu

-0.15

ongs

-0.15

swire

-0.15

isoft

-0.15

ingham

-0.15

sie

-0.15

erland

-0.14

POSITIVE LOGITS

arta

0.19

0.17

 ((((

0.15

 GENERATED

0.15

xFFFFFF

0.14

embro

0.14

 Straw

0.13

 shovel

0.13

.blogspot

0.13

letic

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.