INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

leyen

-0.15

 behavioural

-0.14

 Haram

-0.14

 favourable

-0.14

vil

-0.13

 Honour

-0.13

 Seeder

-0.13

lei

-0.13

patial

-0.13

 ãĥ¼

-0.13

POSITIVE LOGITS

 fucking

0.25

fuck

0.25

 fucks

0.23

 fucked

0.23

 fuck

0.23

 Fucking

0.21

 FUCK

0.20

Fuck

0.20

 Fuck

0.19

 cunt

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.