INDEX

Explanations

variations of the word "imperfection."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ã±as

-0.18

Ø§ÛĮÙĩ

-0.15

sworth

-0.15

slide

-0.15

scribe

-0.15

ird

-0.15

ÑģÐ¾ÑĤ

-0.14

ertas

-0.14

pla

-0.14

POSITIVE LOGITS

fections

0.35

fection

0.32

cept

0.29

atives

0.26

ious

0.26

ium

0.25

manent

0.25

missible

0.25

ish

0.24

me

0.23

Activations Density 0.004%

variations of the word "imperfection."

No Comments

No Known Activations