INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

nev

-0.15

 Mana

-0.14

 IonicModule

-0.14

uby

-0.14

gregar

-0.14

.Spring

-0.13

 incons

-0.13

alam

-0.13

&page

-0.13

ãĥ¼ãĥĦ

-0.13

POSITIVE LOGITS

oin

0.16

essler

0.15

 arrang

0.14

egl

0.14

acht

0.14

bject

0.14

okit

0.14

ution

0.14

 customers

0.14

ollar

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.