INDEX

Explanations

references to legal jurisdictions and state laws

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 rear

-0.14

vier

-0.14

-0.13

 perhaps

-0.13

 confisc

-0.13

bourg

-0.13

ÑĢÐ°Ð´Ð¸

-0.13

 Barg

-0.13

PickerController

-0.13

POSITIVE LOGITS

å·»

0.18

icer

0.18

ÏĥÏĢ

0.16

Ð·Ð¼

0.16

PLICIT

0.16

 disap

0.15

ekler

0.15

armor

0.15

Ð´Ñı

0.15

illard

0.14

Activations Density 0.087%

references to legal jurisdictions and state laws

No Comments

No Known Activations