INDEX

Explanations

terms and phrases related to privacy policies and data handling

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

rech

-0.14

iversal

-0.14

EW

-0.14

xba

-0.14

sea

-0.13

inoa

-0.13

LOAT

-0.13

mic

-0.13

ÏĢÏĮ

-0.13

rees

-0.13

POSITIVE LOGITS

hest

0.16

odzi

0.15

anse

0.15

iswa

0.14

auc

0.14

Ã©r

0.14

dyn

0.14

 pari

0.14

agna

0.14

aman

0.14

Activations Density 0.095%

terms and phrases related to privacy policies and data handling

No Comments

No Known Activations