INDEX

Explanations

programming-related terms and language constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ä¿

-0.18

 hart

-0.16

rosso

-0.16

erties

-0.15

avo

-0.15

rum

-0.14

Ã¡ÅĻ

-0.14

ctors

-0.14

hoff

-0.14

oust

-0.14

POSITIVE LOGITS

 string

0.23

 bool

0.19

 System

0.19

 object

0.19

utex

0.16

 Dictionary

0.15

IGH

0.15

 List

0.15

object

0.15

	string

0.15

Activations Density 0.043%

programming-related terms and language constructs

No Comments

No Known Activations