INDEX

Explanations

references to plans and planning in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 plain

-0.21

 planned

-0.19

angelo

-0.19

Ø®Ø§ÙĨÙĩ

-0.17

.gdx

-0.17

 planning

-0.16

 plaint

-0.16

è¨ĪåĬĥ

-0.16

 ÄĳoÃłn

-0.16

/plain

-0.15

POSITIVE LOGITS

etary

0.31

isphere

0.29

ter

0.25

 Parenthood

0.23

ning

0.23

er

0.20

 ning

0.20

-ahead

0.20

ogram

0.19

egg

0.18

Activations Density 0.058%

references to plans and planning in various contexts

No Comments

No Known Activations