INDEX

Explanations

technical jargon related to radio communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

gro

-0.17

-0.15

ayet

-0.14

 Revel

-0.14

ums

-0.14

MeasureSpec

-0.14

apiro

-0.13

enek

-0.13

Mum

-0.13

onis

-0.13

POSITIVE LOGITS

.parsers

0.15

 hobby

0.15

Gry

0.15

DonaldTrump

0.15

 Hobby

0.14

edList

0.14

 listen

0.14

 TRADE

0.13

toa

0.13

itone

0.13

Activations Density 0.026%

technical jargon related to radio communication

No Comments

No Known Activations