INDEX

Explanations

references to romantic relationships and partnerships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ç¿Ķ

-0.20

eldom

-0.15

iciel

-0.15

yalty

-0.15

ROTO

-0.15

igroup

-0.14

acob

-0.14

literal

-0.14

formace

-0.14

POSITIVE LOGITS

 counter

0.16

çħ

0.15

Fu

0.15

 Orig

0.15

udd

0.14

ng

0.14

 fuels

0.14

ÏĢÎ¿Ïħ

0.14

nuts

0.14

End

0.14

Activations Density 0.075%

references to romantic relationships and partnerships

No Comments

No Known Activations