INDEX

Explanations

technical terms and references related to coding or configuration files

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

Gut

-0.16

NETWORK

-0.15

Fog

-0.15

 contag

-0.15

.gdx

-0.14

 Rust

-0.14

à¥Īà¤¤

-0.14

AZY

-0.13

IONS

-0.13

_pair

-0.13

POSITIVE LOGITS

 carbon

0.28

carbon

0.24

 Carbon

0.23

Carbon

0.23

 Lanka

0.21

à·

0.17

à¶

0.17

Ø§Ø¸

0.17

ãĥ«ãĥķ

0.16

 fault

0.16

Activations Density 0.002%

technical terms and references related to coding or configuration files

No Comments

No Known Activations