INDEX

Explanations

phrases indicating varying degrees of responsibility and professionalism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

OMPI

-0.16

uhn

-0.15

/preferences

-0.14

gota

-0.14

anske

-0.14

ispecies

-0.14

BootApplication

-0.13

jd

-0.13

ÙĤØ±Ø§Ø±

-0.13

POSITIVE LOGITS

 manner

1.11

 fashion

0.94

way

0.91

 Fashion

0.66

 ways

0.65

-fashion

0.62

 maniÃ¨re

0.62

æĸ¹å¼ı

0.62

WAY

0.60

 manera

0.59

Activations Density 0.159%

phrases indicating varying degrees of responsibility and professionalism

No Comments

No Known Activations