INDEX

Explanations

references to animated content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

isel

-0.16

esiz

-0.16

er

-0.15

/>\

-0.15

 hÃ£

-0.14

erate

-0.14

al

-0.14

_hz

-0.14

iton

-0.14

reat

-0.14

POSITIVE LOGITS

osity

0.27

ALES

0.26

advert

0.22

als

0.22

ales

0.20

ALS

0.19

ating

0.18

ojis

0.18

anga

0.18

orph

0.18

Activations Density 0.006%

references to animated content

No Comments

No Known Activations