INDEX

Explanations

references to "Seminole" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

anela

-0.19

iets

-0.19

omer

-0.19

Ð¾Ð¼ÐµÑĢ

-0.16

hec

-0.15

atitude

-0.15

ughters

-0.15

typeorm

-0.15

UZ

-0.15

stav

-0.15

POSITIVE LOGITS

inary

0.28

esters

0.24

antics

0.23

antically

0.22

(sem

0.21

inars

0.21

olina

0.20

sem

0.20

iotics

0.20

Sem

0.19

Activations Density 0.013%

references to "Seminole" and related terms

No Comments

No Known Activations