INDEX

Explanations

references to information and data management

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

hurst

-0.15

lej

-0.15

Ð¾ÐºÐ¾Ð»

-0.15

çĶļ

-0.14

upo

-0.14

htub

-0.14

inou

-0.14

emaker

-0.14

uw

-0.14

iale

-0.14

POSITIVE LOGITS

 technology

0.26

al

0.26

 systems

0.23

technology

0.23

 Technology

0.22

age

0.22

 security

0.21

Age

0.21

ste

0.20

 retrieval

0.20

Activations Density 0.015%

references to information and data management

No Comments

No Known Activations