INDEX

Explanations

references to versatility in products or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

å±¤

-0.15

nze

-0.14

eyer

-0.14

Ð¾Ð¿Ð¸Ñģ

-0.14

tement

-0.14

issant

-0.14

idar

-0.14

ocoa

-0.13

eman

-0.13

ourage

-0.13

POSITIVE LOGITS

ailles

0.32

atile

0.31

atility

0.27

icolor

0.21

 Vers

0.20

uchs

0.20

ace

0.20

pective

0.20

-vers

0.19

 vers

0.19

Activations Density 0.009%

references to versatility in products or subjects

No Comments

No Known Activations