INDEX

Explanations

references to iconic figures and archetypes in pop culture and society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 itself

-0.18

finity

-0.18

iÃ³

-0.16

irts

-0.15

plers

-0.15

-winning

-0.14

lessly

-0.14

igers

-0.14

Ã©is

-0.14

istÃ©

-0.14

POSITIVE LOGITS

who

0.36

who

0.29

 whom

0.28

 whose

0.27

 types

0.26

 type

0.24

whose

0.23

Who

0.21

 quien

0.21

 extra

0.21

Activations Density 0.277%

references to iconic figures and archetypes in pop culture and society

No Comments

No Known Activations