INDEX

Explanations

names of influential individuals in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rette

-0.18

ipur

-0.18

ceptar

-0.15

ipop

-0.15

à¸°à¹ģ

-0.14

adro

-0.14

ÑĢÐ¸Ð·

-0.14

unks

-0.13

porno

-0.13

riere

-0.13

POSITIVE LOGITS

‘

0.15

 torn

0.15

 Ã¢

0.14

cko

0.14

Ìģ

0.14

ze

0.14

FRA

0.14

kin

0.13

tm

0.13

Activations Density 0.348%

names of influential individuals in various fields

No Comments

No Known Activations