INDEX

Explanations

terms related to peer review and peer support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.20

cular

-0.16

itech

-0.15

åĪĢ

-0.14

/features

-0.14

itan

-0.14

usp

-0.14

eve

-0.14

iani

-0.14

 knife

-0.14

POSITIVE LOGITS

-peer

0.27

 peer

0.24

(peer

0.23

-reviewed

0.22

 Peer

0.22

less

0.20

lessly

0.20

Peer

0.19

-review

0.17

peer

0.17

Activations Density 0.006%

terms related to peer review and peer support

No Comments

No Known Activations