INDEX

Explanations

historical and technical terms related to engines or machinery

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

orton

-0.15

smarty

-0.14

fov

-0.14

 ordered

-0.13

xab

-0.13

bedo

-0.13

illet

-0.13

urdu

-0.13

uncio

-0.13

 Mayer

-0.13

POSITIVE LOGITS

 elektr

0.25

Gas

0.24

 mechan

0.24

 Mess

0.23

 pneum

0.23

 Strom

0.23

 elekt

0.22

 Elekt

0.22

Mess

0.21

Gas

0.20

Activations Density 0.020%

historical and technical terms related to engines or machinery

No Comments

No Known Activations