INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 fucked

-0.23

 fuck

-0.21

 shitty

-0.21

 Fuck

-0.20

 FUCK

-0.20

 fucking

-0.19

 Fucking

-0.19

fuck

-0.18

 shit

-0.17

Fuck

-0.17

POSITIVE LOGITS

krom

0.19

 conservatism

0.16

aÄį

0.15

.identity

0.15

 simply

0.15

Ð¾ÑģÑĤÐ¸

0.15

chl

0.14

 understood

0.14

 conservatives

0.14

igon

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.