INDEX

Explanations

structured code snippets and annotations related to user and data handling in software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

rat

-0.18

rat

-0.16

rove

-0.15

ph

-0.15

hel

-0.14

fcn

-0.14

RAT

-0.14

uat

-0.14

angel

-0.14

gh

-0.14

POSITIVE LOGITS

 models

0.24

 Models

0.21

 model

0.21

emodel

0.21

 modÃ¨le

0.21

amodel

0.21

models

0.20

 entities

0.19

_models

0.19

model

0.19

Activations Density 0.090%

structured code snippets and annotations related to user and data handling in software development

No Comments

No Known Activations