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

orget

-0.15

cheid

-0.13

reg

-0.13

vio

-0.13

jet

-0.13

protected

-0.13

 Prism

-0.13

.yahoo

-0.13

nock

-0.13

 Pruitt

-0.12

POSITIVE LOGITS

 asset

0.51

 assets

0.50

asset

0.47

 Assets

0.44

assets

0.43

 Asset

0.42

(asset

0.42

_assets

0.42

Assets

0.41

Asset

0.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.