INDEX

Explanations

phrases related to legal processes and documentation

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

 fibre

-0.18

 knull

-0.16

 whilst

-0.15

 honoured

-0.15

 connexion

-0.15

 favourite

-0.15

 ageing

-0.15

 armour

-0.15

 favourites

-0.14

 aluminium

-0.14

POSITIVE LOGITS

app

0.38

iOS

0.36

 apps

0.35

 iPhone

0.35

App

0.33

 Apps

0.32

 Apple

0.31

iPhone

0.30

 iPad

0.29

iOS

0.29

Activations Density 0.003%

phrases related to legal processes and documentation

No Comments

No Known Activations