INDEX

Explanations

references to visual content and publishing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãĤīãģĽ

-0.15

å¤¢

-0.14

boy

-0.14

uth

-0.14

yn

-0.14

headline

-0.13

lassian

-0.13

 WithEvents

-0.13

 Mist

-0.13

loo

-0.13

POSITIVE LOGITS

 Leer

0.18

igkeit

0.16

nte

0.15

okino

0.15

ï»¿#

0.15

ucha

0.14

ngo

0.14

 republika

0.14

 KÃ¼r

0.14

 DISCLAIM

0.14

Activations Density 0.240%

references to visual content and publishing information

No Comments

No Known Activations