INDEX

Explanations

references to former romantic partners

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

xiety

-0.16

ÐµÐ»Ñİ

-0.15

oust

-0.15

stag

-0.14

apa

-0.14

ajar

-0.14

Ø§ÙħÙĬ

-0.13

jd

-0.13

boards

-0.13

lez

-0.13

POSITIVE LOGITS

/current

0.22

æ¹¯

0.18

ê°ģ

0.15

ovol

0.15

LTR

0.15

/new

0.15

onomies

0.14

odus

0.14

ÑģÑĤÐ²

0.14

oad

0.14

Activations Density 0.009%

references to former romantic partners

No Comments

No Known Activations