INDEX

Explanations

concepts related to control systems and performance metrics

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

licht

-0.19

/umd

-0.17

rella

-0.15

tif

-0.15

uhn

-0.14

izoph

-0.14

declspec

-0.14

 Rays

-0.14

alnÄ±z

-0.13

_ck

-0.13

POSITIVE LOGITS

PID

0.35

 controller

0.29

PID

0.29

pid

0.28

 feedback

0.27

 plant

0.27

_PID

0.26

PI

0.26

 closed

0.25

 controllers

0.25

Activations Density 0.019%

concepts related to control systems and performance metrics

No Comments

No Known Activations