INDEX

Explanations

proper nouns and names associated with notable individuals or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 hence

-0.19

 Hence

-0.16

omon

-0.15

çľī

-0.15

appen

-0.15

éĥİ

-0.15

ãģ¾ãģ¾

-0.15

aub

-0.15

naires

-0.15

ARSER

-0.15

POSITIVE LOGITS

essian

0.20

ERSHEY

0.20

quarter

0.16

iday

0.16

rema

0.16

locker

0.15

OwnProperty

0.15

izons

0.15

itable

0.15

itated

0.15

Activations Density 0.735%

proper nouns and names associated with notable individuals or locations

No Comments

No Known Activations