INDEX

Explanations

mentions of IT-related terms and concepts

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

hist

-0.18

hausen

-0.16

holes

-0.16

itivity

-0.16

hid

-0.15

nock

-0.15

pton

-0.15

âĶĲ

-0.15

Ð½ÑĤ

-0.15

hi

-0.15

POSITIVE LOGITS

unes

0.27

SM

0.25

IL

0.24

SELF

0.21

 infra

0.20

inerary

0.19

 security

0.19

 infrastructure

0.18

sav

0.17

-inf

0.17

Activations Density 0.017%

mentions of IT-related terms and concepts

No Comments

No Known Activations