INDEX

Explanations

phrases and terms related to online activities and transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

phan

-0.18

ainment

-0.15

ILLA

-0.15

 kÃ¶ln

-0.15

oons

-0.14

à¤µà¤¤

-0.14

 norge

-0.14

god

-0.14

 mÃ¼nchen

-0.13

aines

-0.13

POSITIVE LOGITS

ambi

0.16

uil

0.14

ifen

0.14

ãĥĵãĥ¼

0.13

afari

0.13

WithEmailAndPassword

0.13

edb

0.13

 Jako

0.13

ÏĢÏĮ

0.13

 Accord

0.13

Activations Density 0.084%

phrases and terms related to online activities and transactions

No Comments

No Known Activations