INDEX

Explanations

references to specific decades and historical timelines

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

ãĥ¥

-0.19

itur

-0.16

Ã¼tÃ¼n

-0.16

amm

-0.16

utr

-0.15

chein

-0.15

habit

-0.14

amam

-0.14

ÎºÎ¿Ïħ

-0.14

leen

-0.14

POSITIVE LOGITS

å¹´ä»£

0.25

iger

0.23

 Jahre

0.22

lardan

0.20

ies

0.19

ties

0.18

 Jahren

0.18

erne

0.17

er

0.17

 aÃ±os

0.17

Activations Density 0.013%

references to specific decades and historical timelines

No Comments

No Known Activations