INDEX

Explanations

terms related to electromagnetic properties and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ishi

-0.16

IOC

-0.15

aptcha

-0.15

ãĥ£

-0.14

å¤®

-0.14

ierge

-0.14

Slo

-0.13

 centr

-0.13

leneck

-0.13

POSITIVE LOGITS

die

0.29

_die

0.24

die

0.23

Die

0.23

 Fres

0.22

Die

0.22

electric

0.21

 perm

0.21

 electric

0.20

DIE

0.20

Activations Density 0.053%

terms related to electromagnetic properties and measurements

No Comments

No Known Activations