INDEX

Explanations

commands or requests to skip content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

/ay

-0.17

enal

-0.16

aments

-0.15

iyat

-0.15

lak

-0.15

eid

-0.14

locker

-0.14

à¤¹à¤¨

-0.14

estro

-0.14

grily

-0.14

POSITIVE LOGITS

per

0.28

 Skip

0.26

pered

0.25

 skip

0.24

ahead

0.22

 ahead

0.22

cq

0.22

 SKIP

0.21

Skip

0.20

pering

0.20

Activations Density 0.014%

commands or requests to skip content

No Comments

No Known Activations