INDEX

Explanations

references to peer interactions and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

arian

-0.16

 Arte

-0.15

urning

-0.15

eve

-0.15

usp

-0.14

à¤¾à¤

-0.14

 ÐĿÑĸ

-0.14

itech

-0.14

 JpaRepository

-0.14

POSITIVE LOGITS

-peer

0.27

 Peer

0.23

(peer

0.23

 peer

0.22

-reviewed

0.21

Peer

0.20

lessly

0.19

less

0.18

peer

0.16

asma

0.16

Activations Density 0.007%

references to peer interactions and relationships

No Comments

No Known Activations