INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

urance

-0.18

AINER

-0.15

ahlen

-0.14

stan

-0.14

stvÃŃ

-0.14

 field

-0.13

ge

-0.13

uzey

-0.13

 bound

-0.13

 Fault

-0.13

POSITIVE LOGITS

ingen

0.15

à¥įà¤¦

0.14

adia

0.14

ardo

0.14

idUser

0.14

Ø¨Ø§ÙĨ

0.14

acom

0.14

atr

0.13

adan

0.13

lassen

0.13

Activations Density 0.236%

programming-related terms and functions

No Comments

No Known Activations