INDEX

Explanations

programming-related terms and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

_TypeInfo

-0.15

GuidId

-0.15

OptionsResolver

-0.13

UrlParser

-0.13

qli

-0.12

AMED

-0.12

SupportedContent

-0.12

 Sund

-0.12

 Unidos

-0.12

jvu

-0.12

POSITIVE LOGITS

Pos

0.28

pos

0.27

Position

0.26

PosX

0.25

Coords

0.25

Offset

0.25

PosY

0.24

coords

0.24

Radius

0.24

position

0.23

Activations Density 0.295%

programming-related terms and constructs

No Comments

No Known Activations