INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

éĥ

-0.13

enson

-0.13

aka

-0.13

enced

-0.13

ÑĨÑĥ

-0.13

aleb

-0.13

Ã¦kke

-0.13

å®¤

-0.13

amura

-0.13

udem

-0.13

POSITIVE LOGITS

aines

0.15

rana

0.14

ower

0.14

 modem

0.14

 tieten

0.13

OWER

0.13

Activities

0.13

avel

0.13

 activities

0.13

reme

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.