INDEX

Explanations

instances of the word "taken."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ë°©

-0.16

.='

-0.16

yped

-0.15

yk

-0.14

Ø§ÙħÛĮ

-0.14

ca

-0.14

è¹

-0.13

Ups

-0.13

 ____

-0.13

bum

-0.13

POSITIVE LOGITS

'gc

0.18

lili

0.17

oda

0.15

ä¹ħ

0.15

ãĥ³ãĥĲ

0.14

 ãĤ°

0.14

_TP

0.14

.Xaml

0.14

æ¹ĸ

0.14

abi

0.13

Activations Density 0.015%

instances of the word "taken."

No Comments

No Known Activations