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

allest

-0.15

shr

-0.14

anch

-0.14

avra

-0.14

-Men

-0.14

exual

-0.14

oci

-0.14

éļĨ

-0.14

ahoma

-0.14

elmet

-0.14

POSITIVE LOGITS

 Tooth

0.19

Flu

0.18

 fluor

0.18

 fluoride

0.17

 cavity

0.17

cav

0.17

 atoms

0.16

 tooth

0.16

 Stripe

0.15

 lasers

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.