INDEX

Explanations

concepts related to associations and group dynamics

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

vier

-0.16

Ð¾Ð»Ñİ

-0.16

tik

-0.15

okino

-0.14

zano

-0.14

ëĮĢíĸī

-0.14

VRT

-0.13

ichick

-0.13

çīĮ

-0.13

ovalo

-0.13

POSITIVE LOGITS

 membership

0.17

membership

0.17

 organization

0.17

stoff

0.16

 organisation

0.16

 members

0.16

 organizations

0.15

æĪĲåĳĺ

0.15

apus

0.15

_member

0.15

Activations Density 0.031%

concepts related to associations and group dynamics

No Comments

No Known Activations