INDEX

Explanations

instances of authorship and attribution in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ç»į

-0.14

inka

-0.14

Lag

-0.13

yny

-0.13

 Redistributions

-0.13

orre

-0.13

iÅŁtir

-0.12

avig

-0.12

Ä©

-0.12

andon

-0.12

POSITIVE LOGITS

vise

0.16

alley

0.15

aven

0.15

allen

0.14

 cigaret

0.13

dre

0.13

 millenn

0.13

_PCI

0.13

boss

0.12

mj

0.12

Activations Density 0.157%

instances of authorship and attribution in the text

No Comments

No Known Activations