INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Configurer

-0.18

 einfach

-0.15

Î¯Î±ÏĤ

-0.15

.poster

-0.14

/lg

-0.14

 absor

-0.14

allis

-0.14

èĥ

-0.14

acas

-0.14

 IonicModule

-0.14

POSITIVE LOGITS

yre

0.16

ovo

0.15

oves

0.15

 clients

0.15

llen

0.15

 ener

0.14

ogn

0.14

 Slut

0.14

 robust

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.