INDEX

Explanations

specific programming and software development terms or structures

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

ARP

-0.14

ARGV

-0.13

.twig

-0.13

 IconData

-0.13

imos

-0.13

ILD

-0.13

.TryParse

-0.13

odore

-0.13

cra

-0.12

alah

-0.12

POSITIVE LOGITS

;↵

0.33

;↵↵

0.30

0.28

;↵↵↵

0.23

0.22

_;↵

0.21

ï¼Ľ↵

0.21

 ;↵

0.20

;//

0.20

[];↵

0.19

Activations Density 0.068%

specific programming and software development terms or structures

No Comments

No Known Activations