INDEX

Explanations

programming-related terms and function calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ulares

-0.15

alten

-0.15

inson

-0.14

 merry

-0.14

sizeof

-0.14

 longest

-0.14

inch

-0.14

imore

-0.14

ongyang

-0.14

ÄĽÅĻ

-0.14

POSITIVE LOGITS

 integer

0.32

 integers

0.28

 Integer

0.27

integer

0.27

 INTEGER

0.26

Integer

0.25

æķ°åŃĹ

0.24

 numeric

0.24

 parseInt

0.23

.parseInt

0.23

Activations Density 0.226%

programming-related terms and function calls

No Comments

No Known Activations

programming-related terms and function calls

No Comments

No Known Activations