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

ugh

-0.15

adiens

-0.15

upo

-0.14

Å¡t

-0.14

enson

-0.14

teh

-0.14

anik

-0.13

 Duch

-0.13

-era

-0.13

ande

-0.13

POSITIVE LOGITS

.xy

0.15

iverz

0.15

ukan

0.15

ãĥ¬ãĥĥãĥĪ

0.15

 Continent

0.14

omorphic

0.14

arning

0.14

urement

0.14

erdale

0.13

UrlParser

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.