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

 darn

-0.21

Mrs

-0.16

AI

-0.15

 StringBuffer

-0.15

Mrs

-0.15

aza

-0.15

ä»ĬæĹ¥

-0.14

 wife

-0.14

AI

-0.13

onga

-0.13

POSITIVE LOGITS

 fucked

0.25

 fucks

0.24

 fuck

0.22

 cunt

0.21

 FUCK

0.21

 Fuck

0.21

Fuck

0.20

fuck

0.19

 Fucked

0.19

 dicks

0.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.