INDEX

Explanations

references to personal websites, blogs, and online content management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

lege

-0.17

 Rosen

-0.16

iosk

-0.15

merce

-0.15

áº¡nh

-0.15

ilib

-0.14

atura

-0.14

urg

-0.13

ingles

-0.13

lok

-0.13

POSITIVE LOGITS

Schedulers

0.16

inka

0.15

 Higgins

0.14

cline

0.14

wu

0.14

 Benton

0.14

erde

0.13

 Matcher

0.13

íĬ

0.13

Foreground

0.13

Activations Density 0.016%

references to personal websites, blogs, and online content management

No Comments

No Known Activations