INDEX

Explanations

technical terms and concepts related to measurements and standards in engineering or science

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

EventHandler

-0.16

dech

-0.14

Ø°

-0.14

ProcAddress

-0.14

osg

-0.13

reb

-0.13

 depr

-0.13

Åł

-0.13

ACH

-0.13

agate

-0.13

POSITIVE LOGITS

 imped

0.26

 react

0.23

adm

0.23

 impedance

0.22

 lump

0.22

_imp

0.21

 Reactive

0.21

React

0.21

 reactive

0.20

éĺ»

0.20

Activations Density 0.042%

technical terms and concepts related to measurements and standards in engineering or science

No Comments

No Known Activations