INDEX

Explanations

questions and phrases that express curiosity or uncertainty

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

erta

-0.17

nist

-0.15

imary

-0.15

incy

-0.13

è¦

-0.13

ocale

-0.13

rika

-0.13

shade

-0.13

eref

-0.13

iment

-0.13

POSITIVE LOGITS

 much

0.32

much

0.27

 little

0.25

Much

0.22

itzer

0.22

 many

0.22

 Much

0.21

few

0.20

 wrong

0.20

 alike

0.20

Activations Density 0.045%

questions and phrases that express curiosity or uncertainty

No Comments

No Known Activations