INDEX

Explanations

programming-related terms, particularly those involved in method calls and data retrieval within a service context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.25

-0.20

("'"

-0.19

(UIAlertAction

-0.19

('</

-0.18

-0.17

POSITIVE LOGITS

(↵

0.46

("

0.37

();↵

0.33

('

0.33

()↵

0.32

().

0.32

0.31

();↵↵

0.31

((

0.31

ï¼Ī

0.30

Activations Density 0.213%

programming-related terms, particularly those involved in method calls and data retrieval within a service context

No Comments

No Known Activations

programming-related terms, particularly those involved in method calls and data retrieval within a service context

No Comments

No Known Activations