INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

éģ

-0.17

BuilderInterface

-0.15

irts

-0.14

kus

-0.14

uala

-0.14

vous

-0.14

ffset

-0.13

ÅĤem

-0.13

aisal

-0.13

 rÃ¡d

-0.13

POSITIVE LOGITS

wom

0.15

jem

0.14

afc

0.14

 facility

0.13

til

0.13

ÏĥÎ¹

0.13

Col

0.13

col

0.13

icol

0.13

gis

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.