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

subst

-0.14

jed

-0.14

UGE

-0.14

 Outlet

-0.13

 LENG

-0.13

-defense

-0.13

_CYCLE

-0.13

Ã¶t

-0.13

uche

-0.13

 Lesser

-0.13

POSITIVE LOGITS

 coaching

0.29

 Coaching

0.28

 money

0.23

 coaches

0.22

 Money

0.22

 coached

0.22

 Client

0.21

 coach

0.21

Client

0.20

 Coach

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.