INDEX

Explanations

references to prior articles or posts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

akov

-0.17

aldo

-0.15

ixture

-0.15

oku

-0.14

onna

-0.14

voke

-0.14

WG

-0.14

ekli

-0.14

_REUSE

-0.14

åħ¼

-0.14

POSITIVE LOGITS

 article

0.31

 Article

0.28

 Post

0.27

 Previous

0.27

Previous

0.26

 post

0.24

 story

0.22

 Entry

0.21

 Story

0.20

 artikel

0.18

Activations Density 0.011%

references to prior articles or posts

No Comments

No Known Activations