INDEX

Explanations

references to foundational principles or frameworks based on empirical data

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

iba

-0.16

quoise

-0.15

µľ

-0.15

okino

-0.14

ADE

-0.14

/Dk

-0.14

Éµ

-0.14

orelease

-0.14

enci

-0.14

qua

-0.13

POSITIVE LOGITS

 experience

0.35

 experiences

0.31

 principles

0.29

 observations

0.29

 observation

0.28

experience

0.27

 principle

0.27

 feedback

0.26

 input

0.25

observations

0.24

Activations Density 0.307%

references to foundational principles or frameworks based on empirical data

No Comments

No Known Activations