INDEX

Explanations

references to educational institutions and collaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

equ

-0.15

maz

-0.15

lix

-0.15

paging

-0.15

hl

-0.15

oÅ¾

-0.14

 Ø¢ÙĦ

-0.14

edis

-0.14

prom

-0.14

 posters

-0.13

POSITIVE LOGITS

(PC

0.26

PP

0.21

(PR

0.20

PC

0.19

PW

0.18

PQ

0.17

(PHP

0.17

PN

0.16

CP

0.15

(KP

0.15

Activations Density 0.146%

references to educational institutions and collaborations

No Comments

No Known Activations