INDEX

Explanations

symbols and modifiers related to object properties in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

PLIC

-0.15

chen

-0.15

akov

-0.15

Kad

-0.14

Ãłnh

-0.14

ovsky

-0.14

 Canton

-0.14

inals

-0.14

oslav

-0.14

apult

-0.14

POSITIVE LOGITS

ZN

0.19

ozo

0.18

Nonnull

0.16

JEXEC

0.15

.configuration

0.15

ga

0.14

ente

0.14

uky

0.13

nte

0.13

 persever

0.13

Activations Density 0.032%

symbols and modifiers related to object properties in code

No Comments

No Known Activations