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

 ↵↵

-0.15

azen

-0.14

aze

-0.14

åĭŁ

-0.13

laden

-0.13

azed

-0.13

Loads

-0.13

.codes

-0.13

ajes

-0.13

ï»¿#

-0.13

POSITIVE LOGITS

 waterproof

0.18

 seal

0.17

mak

0.17

Ki

0.16

 real

0.15

 seam

0.15

isoft

0.15

 Waterproof

0.15

llu

0.15

 mana

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.