INDEX

Explanations

mentions of personally identifiable information and consent related to data privacy

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elize

-0.17

eldorf

-0.16

aravel

-0.15

edly

-0.15

urus

-0.14

itionally

-0.14

icensing

-0.14

 Headquarters

-0.14

è®

-0.13

à¸¢à¸°

-0.13

POSITIVE LOGITS

Ð¾Ð¿ÑĢÐ¸

0.16

0.14

ynos

0.13

IFI

0.13

Ka

0.13

SOP

0.13

inta

0.13

rung

0.13

lenÃŃ

0.13

 Lyons

0.13

Activations Density 0.030%

mentions of personally identifiable information and consent related to data privacy

No Comments

No Known Activations