INDEX

Explanations

references to cooking and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

izer

-0.18

portlet

-0.17

udi

-0.17

usher

-0.16

ario

-0.15

izio

-0.14

izard

-0.14

uously

-0.14

POSITIVE LOGITS

ingham

0.18

tober

0.17

 advent

0.17

PAD

0.17

ery

0.17

oÅĻ

0.16

erman

0.16

liness

0.16

Kut

0.16

¬

0.15

Activations Density 0.023%

references to cooking and related activities

No Comments

No Known Activations