INDEX

Explanations

references to historical reenactments and demonstrations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

aida

-0.15

omik

-0.15

ennent

-0.14

ski

-0.14

hiba

-0.14

 legends

-0.13

Pointer

-0.13

->__

-0.13

 ÑģÐ¾Ð±

-0.13

 Politics

-0.13

POSITIVE LOGITS

 auth

0.26

 recre

0.25

 authentic

0.25

 recreated

0.24

 authenticity

0.24

 period

0.24

 Authentic

0.23

 recreate

0.22

 Historic

0.21

auth

0.21

Activations Density 0.139%

references to historical reenactments and demonstrations

No Comments

No Known Activations