INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

&p

-0.14

('__

-0.14

erin

-0.14

VM

-0.14

æĽľ

-0.14

Ãİ

-0.13

 weren

-0.13

 Rica

-0.13

 emanc

-0.13

 Marketable

-0.13

POSITIVE LOGITS

reff

0.16

 utilization

0.15

 usage

0.15

emann

0.15

 male

0.15

 males

0.14

aco

0.14

oc

0.14

male

0.13

uy

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.