INDEX

Explanations

mentions of HTML-related terms and code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

es

-0.19

esis

-0.16

ek

-0.16

ģ

-0.15

ese

-0.15

hood

-0.15

aging

-0.15

icer

-0.14

lando

-0.14

 Voor

-0.14

POSITIVE LOGITS

WebpackPlugin

0.26

 PUBLIC

0.25

ayout

0.23

DivElement

0.22

/javascript

0.20

InputElement

0.20

 Agility

0.19

[dir

0.18

/css

0.18

Activations Density 0.034%

mentions of HTML-related terms and code

No Comments

No Known Activations