INDEX

Explanations

phrases and concepts related to planning and organization

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

hol

-0.15

 createContext

-0.15

ahi

-0.15

kv

-0.15

Ð¾Ð

-0.15

ÄĻd

-0.14

artz

-0.14

inear

-0.14

jev

-0.13

ovel

-0.13

POSITIVE LOGITS

.hxx

0.18

agn

0.15

 Rosenstein

0.15

 Lyon

0.14

ÄŁan

0.14

.ast

0.14

ë¡ł

0.14

ë²Į

0.13

 VerfÃ¼g

0.13

uml

0.13

Activations Density 2.038%

phrases and concepts related to planning and organization

No Known Activations