INDEX

Explanations

references to individuals and organizations involved in governance and public policy

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ept

-0.16

stem

-0.15

edy

-0.15

ÏĨÏħ

-0.14

uff

-0.14

 unions

-0.14

ÙħÙĪÙĦ

-0.14

nic

-0.14

ÐµÑİ

-0.13

ectors

-0.13

POSITIVE LOGITS

obraz

0.17

onse

0.14

setattr

0.14

 èĩ

0.14

ational

0.14

 à¤ķà¤ª

0.14

AMAGE

0.13

Uniform

0.13

oley

0.13

etchup

0.13

Activations Density 0.568%

references to individuals and organizations involved in governance and public policy

No Comments

No Known Activations