INDEX

Explanations

references to popular culture and entertainment

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

ALAR

-0.16

 NavParams

-0.15

opro

-0.15

 Bauer

-0.14

PW

-0.14

ogo

-0.14

apiro

-0.14

ancel

-0.13

opped

-0.13

heim

-0.13

POSITIVE LOGITS

mas

0.25

axter

0.21

mas

0.20

 commercial

0.19

 reel

0.18

 mast

0.18

Mas

0.18

 Commercial

0.17

ItemList

0.17

 Mast

0.17

Activations Density 0.031%

references to popular culture and entertainment

No Comments

No Known Activations