INDEX

Explanations

references to oaths, vows, and commitments

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

.metamodel

-0.17

hread

-0.16

opis

-0.16

ordion

-0.16

-0.15

ÐĲÑĢÑħÑĸÐ²

-0.15

Insensitive

-0.14

mÃŃt

-0.14

Ú¯Ø±ÛĮ

-0.14

AutoSize

-0.14

POSITIVE LOGITS

 oath

0.47

 swearing

0.35

 sworn

0.34

 swear

0.33

0.32

 vows

0.31

 pledge

0.31

vow

0.31

èª

0.29

 pledges

0.27

Activations Density 0.061%

references to oaths, vows, and commitments

No Comments

No Known Activations