INDEX

Explanations

phrases related to academic recognition and rankings

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

rosso

-0.17

oÅ¾

-0.17

æĹħ

-0.15

cel

-0.15

elo

-0.15

ulan

-0.14

/loader

-0.14

çµ±

-0.14

erto

-0.14

/commons

-0.14

POSITIVE LOGITS

QS

0.35

QS

0.30

 Times

0.26

Times

0.22

qs

0.20

0.19

 TIMES

0.18

 employers

0.18

 employ

0.18

qs

0.18

Activations Density 0.018%

phrases related to academic recognition and rankings

No Comments

No Known Activations