INDEX

Explanations

terminology related to control systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

control

-0.27

_control

-0.26

 control

-0.26

Control

-0.25

_controls

-0.24

 kontrol

-0.23

 Control

-0.23

 controls

-0.23

_ctrl

-0.22

controls

-0.21

POSITIVE LOGITS

led

0.35

ateral

0.30

ador

0.27

leur

0.23

 freak

0.23

adores

0.22

.Monad

0.20

adora

0.20

 Freak

0.19

ADOR

0.19

Activations Density 0.043%

terminology related to control systems

No Comments

No Known Activations