INDEX

Explanations

references to public events and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

rech

-0.15

 colspan

-0.14

 ReturnValue

-0.14

á»Ļc

-0.13

athom

-0.13

å¸Ń

-0.13

croft

-0.13

TabControl

-0.13

è¿İ

-0.13

unan

-0.13

POSITIVE LOGITS

 inspect

0.30

 inspection

0.30

 examination

0.28

inspect

0.26

 examine

0.26

Inspect

0.25

 examining

0.25

 inspections

0.24

 inspected

0.24

 Inspection

0.23

Activations Density 0.198%

references to public events and activities

No Comments

No Known Activations