INDEX

Explanations

technical terminology and references related to programming and market activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

/animations

-0.18

apiro

-0.17

itchens

-0.16

anio

-0.16

eyim

-0.15

ocha

-0.15

dorf

-0.14

Ĥæķ°

-0.14

áºŃu

-0.14

à¥įà¤¬à¤¨

-0.14

POSITIVE LOGITS

ocz

0.17

met

0.16

micro

0.16

 Shed

0.15

 catches

0.14

catch

0.14

 Dawson

0.14

 shed

0.14

oup

0.14

cancel

0.13

Activations Density 0.001%

technical terminology and references related to programming and market activities

No Comments

No Known Activations