INDEX

Explanations

references to sequences or ordering of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 rowspan

-0.15

ouro

-0.14

iano

-0.14

ovid

-0.14

uae

-0.13

å¢¨

-0.13

 Ingram

-0.13

ieber

-0.13

expand

-0.13

inders

-0.13

POSITIVE LOGITS

 order

0.58

 Order

0.48

order

0.47

Order

0.46

 ORDER

0.46

éłĨ

0.46

é¡º

0.46

-order

0.45

ORDER

0.42

_order

0.42

Activations Density 0.169%

references to sequences or ordering of items

No Comments

No Known Activations