INDEX

Explanations

instances of the word "test" and related terms 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ÑģÑĮ

-0.19

heid

-0.18

ly

-0.17

ARGE

-0.17

osate

-0.16

fter

-0.16

faker

-0.16

isms

-0.16

zeitig

-0.16

ely

-0.16

POSITIVE LOGITS

imonial

0.30

imony

0.30

imonials

0.30

osterone

0.29

icular

0.24

.UnitTesting

0.22

containers

0.20

aments

0.19

icles

0.19

ifies

0.19

Activations Density 0.084%

instances of the word "test" and related terms in various contexts

No Comments

No Known Activations