INDEX

Explanations

code-related terms associated with function definitions and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ardu

-0.17

Ì§

-0.15

/__

-0.15

Ð¾Ð²Ð°ÑĢÐ¸

-0.15

,[

-0.14

OTES

-0.14

/inet

-0.14

èļ

-0.14

DBObject

-0.14

Ã¡b

-0.14

POSITIVE LOGITS

 func

0.30

nil

0.26

[]

0.26

<-

0.26

 strings

0.23

([]

0.23

func

0.23

 append

0.23

(func

0.21

 strconv

0.21

Activations Density 0.021%

code-related terms associated with function definitions and programming constructs

No Comments

No Known Activations