INDEX

Explanations

references to logging functionality in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

lings

-0.17

xdb

-0.14

engin

-0.14

 Brend

-0.13

Fee

-0.13

tsy

-0.13

CISION

-0.13

raig

-0.13

 Ã§ap

-0.13

POSITIVE LOGITS

Paren

0.17

argo

0.16

ÑĪÐºÐ°

0.15

esar

0.15

LETED

0.14

aled

0.14

alth

0.14

 Stre

0.14

æŀ

0.13

cdn

0.13

Activations Density 0.027%

references to logging functionality in code

No Comments

No Known Activations