INDEX

Explanations

programming and coding-related terms, particularly those associated with classes, data structures, and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

kud

-0.17

ombres

-0.14

oulder

-0.14

ritch

-0.13

asm

-0.13

yb

-0.13

 UITableView

-0.13

Disposable

-0.13

agan

-0.12

Cz

-0.12

POSITIVE LOGITS

 extends

0.34

 extend

0.26

 :↵

0.22

 extending

0.22

 implements

0.21

 {↵↵

0.20

 :↵↵

0.20

extends

0.20

 {↵

0.19

Activations Density 0.026%

programming and coding-related terms, particularly those associated with classes, data structures, and services

No Comments

No Known Activations