INDEX

Explanations

terms related to historical and geographical contexts, especially concerning governance and cultural heritage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 none

-0.14

Tube

-0.13

Thunk

-0.13

iras

-0.13

 ragaz

-0.13

ADF

-0.13

IDA

-0.13

 ÐµÐ»ÐµÐºÑĤÑĢÐ¾Ð½

-0.13

umbn

-0.13

 once

-0.13

POSITIVE LOGITS

en

0.34

die

0.28

wa

0.21

Die

0.21

tez

0.20

Die

0.19

 mÃ©t

0.19

 want

0.19

,en

0.19

met

0.19

Activations Density 0.043%

terms related to historical and geographical contexts, especially concerning governance and cultural heritage

No Comments

No Known Activations