INDEX

Explanations

phrases that indicate possession or relationships between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

quests

-0.15

idot

-0.14

æĥħ

-0.14

fav

-0.14

quee

-0.14

ottom

-0.14

opis

-0.13

ä¸ĢåĪĩ

-0.13

kÃ¼

-0.13

arters

-0.13

POSITIVE LOGITS

 sorts

0.41

 note

0.29

 interest

0.28

 course

0.25

course

0.25

 choice

0.24

 relevance

0.24

ft

0.23

 kinds

0.23

icina

0.23

Activations Density 0.430%

phrases that indicate possession or relationships between entities

No Comments

No Known Activations