INDEX

Explanations

expressions of positivity and emotional depth in relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

idir

-0.15

ukt

-0.15

opensource

-0.15

apro

-0.15

peria

-0.15

èį·

-0.14

[|

-0.14

ulumi

-0.14

ITIVE

-0.14

ocz

-0.14

POSITIVE LOGITS

 alone

0.15

igin

0.15

ble

0.15

AEA

0.15

ambre

0.14

æ´ĭ

0.13

ements

0.13

bling

0.13

ÑĢÐ¾ÑģÑĤ

0.13

ling

0.13

Activations Density 0.358%

expressions of positivity and emotional depth in relationships

No Comments

No Known Activations