INDEX

Explanations

references to popular music or artists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

itoris

-0.18

vig

-0.16

ungan

-0.15

etheus

-0.14

uvre

-0.14

Dip

-0.14

wang

-0.14

ertino

-0.14

azole

-0.14

decess

-0.14

POSITIVE LOGITS

Ã³ÅĤ

0.30

raw

0.29

rowad

0.28

ami

0.27

ÅĤy

0.26

ier

0.26

ÅĤ

0.25

omi

0.24

oni

0.23

ows

0.23

Activations Density 0.009%

references to popular music or artists

No Comments

No Known Activations