INDEX

Explanations

words related to exploration and discovery

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

allis

-0.18

ingle

-0.16

comings

-0.15

icho

-0.15

elman

-0.15

eldon

-0.15

¹Ħ

-0.15

etur

-0.15

_ATT

-0.14

iddles

-0.14

POSITIVE LOGITS

ainer

0.33

oring

0.32

ained

0.32

aining

0.31

oration

0.28

ains

0.27

oding

0.27

oded

0.26

ainers

0.25

AINER

0.25

Activations Density 0.004%

words related to exploration and discovery

No Comments

No Known Activations