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

rud

-0.14

ä¸Ģçº§

-0.14

PERT

-0.14

heits

-0.14

ublik

-0.14

atti

-0.13

terr

-0.13

tra

-0.13

hist

-0.13

 cade

-0.13

POSITIVE LOGITS

Haj

0.18

 Studio

0.17

 animate

0.17

Studio

0.17

 Area

0.17

Licensed

0.16

anime

0.16

 animation

0.16

 animated

0.16

 anime

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.