INDEX

Explanations

references to privacy policies and terms of service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

andler

-0.17

zcze

-0.16

æ´²

-0.16

Å¡ov

-0.15

irling

-0.15

ÑĸÐ»ÑĮÑĪ

-0.15

uin

-0.14

bob

-0.14

 equip

-0.14

entifier

-0.14

POSITIVE LOGITS

 privacy

0.18

Privacy

0.18

powered

0.17

 copp

0.17

privacy

0.17

 Privacy

0.16

 disclaimer

0.16

Powered

0.16

itos

0.16

ÏīÎ½

0.15

Activations Density 0.018%

references to privacy policies and terms of service

No Comments

No Known Activations