INDEX

Explanations

references to historical timelines and periods

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

upo

-0.15

Ctrls

-0.15

Spi

-0.14

imest

-0.14

è¼ª

-0.14

ReadStream

-0.13

neas

-0.13

ÑĶÐ¼

-0.13

LES

-0.13

 period

-0.13

POSITIVE LOGITS

 siguiente

0.23

 suiv

0.23

 siguientes

0.20

 seguint

0.19

 poster

0.19

 anterior

0.19

iguiente

0.19

 following

0.18

 posterior

0.18

 preced

0.17

Activations Density 0.022%

references to historical timelines and periods

No Known Activations