INDEX

Explanations

the structure and formatting of film reviews, including titles and release years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ublish

-0.16

ListOf

-0.15

DataStream

-0.14

ugg

-0.14

FRING

-0.14

ugins

-0.14

IRS

-0.14

omik

-0.14

reate

-0.14

CONS

-0.14

POSITIVE LOGITS

Pixels

0.21

 Venom

0.20

 Maze

0.20

 Suicide

0.19

Sic

0.19

Aqu

0.18

Padding

0.18

 Deadpool

0.18

 Padding

0.17

 Kings

0.17

Activations Density 0.116%

the structure and formatting of film reviews, including titles and release years

No Comments

No Known Activations