INDEX

Explanations

terms related to research, policy, and program development in various sectors

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

ä¼Ļ

-0.17

ouchers

-0.15

iset

-0.14

avig

-0.14

uned

-0.14

ColorBrush

-0.14

blick

-0.14

prs

-0.14

iffe

-0.14

umas

-0.14

POSITIVE LOGITS

 management

0.25

 aspects

0.24

 services

0.24

 issues

0.22

 matters

0.22

 analysis

0.22

 support

0.21

 stuff

0.20

æĸ¹éĿ¢

0.20

 consulting

0.19

Activations Density 0.238%

terms related to research, policy, and program development in various sectors

No Comments

No Known Activations