INDEX

Explanations

references to the term "self" in object-oriented programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ault

-0.16

hip

-0.16

logy

-0.15

.SIG

-0.14

phan

-0.14

Ã¼b

-0.14

ÑģÑĥ

-0.14

file

-0.14

ful

-0.13

ÑģÑĮ

-0.13

POSITIVE LOGITS

iterals

0.16

ieber

0.16

ĵn

0.14

rosse

0.14

eway

0.14

erson

0.14

ursor

0.14

mÃ©na

0.14

OCUS

0.14

enn

0.14

Activations Density 0.005%

references to the term "self" in object-oriented programming contexts

No Comments

No Known Activations