INDEX

Explanations

alphanumeric codes and references in various formats

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

bury

-0.20

burst

-0.17

amental

-0.16

bag

-0.16

bruar

-0.16

bubble

-0.15

decltype

-0.15

bear

-0.15

bulan

-0.15

berger

-0.14

POSITIVE LOGITS

etween

0.35

usiness

0.35

eyond

0.33

ecause

0.32

reak

0.32

efore

0.32

udget

0.31

rown

0.31

ased

0.31

asic

0.31

Activations Density 0.089%

alphanumeric codes and references in various formats

No Comments

No Known Activations