INDEX

Explanations

references to secrecy or confidential matters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ëĿ½

-0.18

eled

-0.16

oley

-0.15

alez

-0.15

 è»Ĭ

-0.15

tures

-0.15

ya

-0.15

ales

-0.14

ptr

-0.14

ping

-0.14

POSITIVE LOGITS

ariat

0.40

arial

0.37

iveness

0.30

aries

0.29

 secret

0.25

ively

0.25

ive

0.25

(secret

0.25

Ã¡ria

0.24

ory

0.24

Activations Density 0.015%

references to secrecy or confidential matters

No Comments

No Known Activations