INDEX

Explanations

conditional statements and logical evaluations in code

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

eliac

-0.16

dra

-0.16

iao

-0.14

itou

-0.14

eger

-0.14

 jadx

-0.14

DeV

-0.14

ival

-0.14

ìŀ¡ëĭ´

-0.14

 Elli

-0.13

POSITIVE LOGITS

 typeof

0.44

typeof

0.37

(typeof

0.35

 Array

0.22

 isinstance

0.21

.isArray

0.20

 Object

0.19

Array

0.18

ä¹ĭ

0.18

(Array

0.18

Activations Density 0.236%

conditional statements and logical evaluations in code

No Comments

No Known Activations