INDEX

Explanations

references to various types and attributes of "states" or "conditions."

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

lint

-0.17

Malloc

-0.16

 discretion

-0.16

ãĤ©

-0.16

 Ð´Ð¾Ñģ

-0.15

ido

-0.15

 shores

-0.15

edback

-0.15

 opportunity

-0.14

ipples

-0.14

POSITIVE LOGITS

rut

0.30

 state

0.26

 bind

0.26

 funk

0.23

 binds

0.23

 coma

0.22

 Bind

0.21

bind

0.21

 groove

0.21

 slump

0.20

Activations Density 0.086%

references to various types and attributes of "states" or "conditions."

No Comments

No Known Activations