INDEX

Explanations

phrases related to warnings and precautions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 teenager

-0.17

Fan

-0.16

vendor

-0.15

utor

-0.15

ponent

-0.15

ighbor

-0.15

 stranger

-0.14

Fan

-0.14

ician

-0.14

 insurer

-0.13

POSITIVE LOGITS

 users

0.28

 participants

0.28

participants

0.23

 individuals

0.22

users

0.22

 subjects

0.20

 contributors

0.20

 potential

0.20

 Users

0.20

 consumers

0.20

Activations Density 0.462%

phrases related to warnings and precautions in various contexts

No Comments

No Known Activations