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

éļĨ

-0.15

oho

-0.14

 Rear

-0.14

eka

-0.14

.Interop

-0.14

 Bang

-0.14

ulum

-0.14

 rear

-0.14

oram

-0.14

 innov

-0.14

POSITIVE LOGITS

 away

0.16

agg

0.15

agem

0.15

upd

0.14

elter

0.14

pherd

0.14

 porr

0.14

 Salvador

0.14

ÐµÐ½Ð¸Ð¼

0.14

ibold

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.