INDEX

Explanations

references to various models or methodologies

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

ally

-0.22

es

-0.21

_models

-0.19

aches

-0.17

_model

-0.17

fulness

-0.17

Model

-0.16

Models

-0.16

asaki

-0.16

 modeled

-0.16

POSITIVE LOGITS

led

0.53

ë§ģ

0.27

ocked

0.26

LED

0.25

ocking

0.25

lo

0.24

ledon

0.21

.addAttribute

0.21

ers

0.20

lica

0.20

Activations Density 0.038%

references to various models or methodologies

No Comments

No Known Activations