INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

»

-0.15

uyÃªn

-0.15

illac

-0.14

ç¸

-0.14

PropTypes

-0.14

PTH

-0.13

ppard

-0.13

à¸Ńà¸Ļ

-0.13

_dispatch

-0.13

Âłmph

-0.13

POSITIVE LOGITS

ĵåĲį

0.17

inois

0.16

 Citizen

0.16

tement

0.16

 https

0.15

 Replies

0.15

 Pole

0.15

 realtime

0.15

uff

0.14

Ð±Ð¾

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.