INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

eel

-0.18

ucas

-0.15

gary

-0.14

egin

-0.14

 kÃ¥

-0.14

 funky

-0.13

azure

-0.13

ÃŃÅ¡

-0.13

avar

-0.13

ë¥

-0.13

POSITIVE LOGITS

 Angus

0.16

fÃ¶r

0.14

ersions

0.14

rel

0.14

 Zahl

0.14

.Toolkit

0.13

ozÃŃ

0.13

oha

0.13

oldem

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.