INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Shak

-0.17

uzzi

-0.16

ylv

-0.14

Ã¯

-0.14

olk

-0.14

 Vill

-0.14

onn

-0.14

Ny

-0.14

Wy

-0.14

POSITIVE LOGITS

 Äĳ

0.17

 tome

0.16

Ñ

0.15

ndon

0.15

cev

0.15

asje

0.15

unar

0.14

.rs

0.14

&&!

0.14

rst

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.