INDEX

Explanations

references to philosophical concepts or figures, particularly in relation to Objectivism and value systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

elu

-0.15

Å¡ku

-0.15

mlink

-0.14

ucene

-0.14

ä»·

-0.13

ucci

-0.13

ONO

-0.13

 Balance

-0.13

 Vladim

-0.13

batis

-0.13

POSITIVE LOGITS

 Rand

0.21

/rand

0.19

 Atlas

0.19

 peaceful

0.19

Hay

0.18

usta

0.18

Atlas

0.17

 Roth

0.17

Rand

0.17

 Ludwig

0.17

Activations Density 0.026%

references to philosophical concepts or figures, particularly in relation to Objectivism and value systems

No Comments

No Known Activations