INDEX

Explanations

locations and settings relevant to historical or cultural events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Bounty

-0.16

resar

-0.15

oop

-0.15

uang

-0.15

rypton

-0.14

Orm

-0.14

 pixmap

-0.14

owell

-0.14

eos

-0.14

POSITIVE LOGITS

 Jerusalem

0.30

Jer

0.27

Jer

0.24

jer

0.23

 Temple

0.22

 oslo

0.21

jer

0.19

hol

0.18

 holy

0.18

 sensit

0.18

Activations Density 0.040%

locations and settings relevant to historical or cultural events

No Comments

No Known Activations