INDEX

Explanations

auxiliary verbs indicating actions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

å®Ļ

-0.17

ancode

-0.16

ezi

-0.16

DataTask

-0.15

Ð»Ð¸Ðº

-0.15

/GPL

-0.15

 Wich

-0.14

zag

-0.14

ÐµÐ»Ð¸Ñĩ

-0.14

 ApplicationException

-0.14

POSITIVE LOGITS

ent

0.37

0.32

’

0.30

nt

0.30

nt

0.30

't

0.29

’t

0.29

'n

0.24

en

0.24

na

0.23

Activations Density 0.087%

auxiliary verbs indicating actions or states of being

No Comments

No Known Activations