INDEX

Explanations

code-related terms and functions involving serialization and deserialization processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

anders

-0.17

 Bever

-0.16

ÑģÑĤÐ°Ð½Ð¾Ð²

-0.16

ê´

-0.15

HashSet

-0.14

.intValue

-0.14

smith

-0.14

HashTable

-0.14

inkle

-0.14

 Gale

-0.14

POSITIVE LOGITS

 bytes

0.25

 byte

0.24

 memory

0.23

 QByteArray

0.23

(byte

0.23

 ByteBuffer

0.22

(bytes

0.22

NSData

0.22

 NSData

0.21

.toByteArray

0.21

Activations Density 0.164%

code-related terms and functions involving serialization and deserialization processes

No Comments

No Known Activations