INDEX

Explanations

technical terms related to computer systems and encryption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

vat

-0.16

omo

-0.15

 Encoder

-0.15

Eh

-0.15

ocoa

-0.14

umm

-0.14

ican

-0.14

inya

-0.14

amed

-0.14

_ENCOD

-0.14

POSITIVE LOGITS

 hardware

0.23

 security

0.22

 trust

0.21

att

0.21

 Hardware

0.20

TPM

0.20

 Trust

0.20

tam

0.20

 attest

0.19

TEE

0.19

Activations Density 0.021%

technical terms related to computer systems and encryption

No Comments

No Known Activations