INDEX

Explanations

references to authorship and attribution in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ary

-0.18

Î¯ÏīÎ½

-0.17

ody

-0.16

-eyed

-0.16

yor

-0.16

enie

-0.15

esz

-0.15

emens

-0.15

artin

-0.14

æĺŃåĴĮ

-0.14

POSITIVE LOGITS

ship

0.30

itative

0.28

itarian

0.25

ised

0.22

ial

0.20

SHIP

0.19

ing

0.19

izations

0.19

ISED

0.18

izing

0.17

Activations Density 0.027%

references to authorship and attribution in texts

No Comments

No Known Activations

references to authorship and attribution in texts

No Comments

No Known Activations