INDEX

Explanations

references to academic publications and peer-reviewed research

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

Studio

-0.18

studio

-0.17

 Studio

-0.16

 Compiled

-0.15

 bree

-0.14

_ENTER

-0.14

 åķ

-0.14

HN

-0.13

ÃŃl

-0.13

dÃŃ

-0.13

POSITIVE LOGITS

 publication

0.36

 paper

0.32

 published

0.31

 publications

0.30

 publish

0.30

publication

0.29

 papers

0.28

 pubs

0.27

 abstract

0.25

 Publication

0.25

Activations Density 0.190%

references to academic publications and peer-reviewed research

No Comments

No Known Activations