INDEX

Explanations

references to social media interactions and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

anzi

-0.17

oho

-0.14

Ø¬Ø¨

-0.14

ove

-0.14

ÑĮÐµÑĢ

-0.14

akers

-0.14

Ãłu

-0.14

ooter

-0.14

wen

-0.14

orb

-0.14

POSITIVE LOGITS

 profile

0.26

 Profile

0.25

 PROFILE

0.23

profile

0.23

Profile

0.22

bio

0.22

(profile

0.21

_profile

0.21

 profiles

0.20

/profile

0.20

Activations Density 0.062%

references to social media interactions and updates

No Comments

No Known Activations