INDEX

Explanations

phrases related to future planning and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

kke

-0.16

jiang

-0.15

lander

-0.15

phia

-0.14

aign

-0.14

kish

-0.14

ANGO

-0.14

.fromString

-0.13

 Yesterday

-0.13

 ãĥŀ

-0.13

POSITIVE LOGITS

 ná»¯a

0.20

Âłtom

0.19

 next

0.19

 lagi

0.18

 again

0.17

à¸łà¸²à¸ŀ

0.17

 future

0.17

 similarly

0.15

 further

0.15

hint

0.15

Activations Density 0.197%

phrases related to future planning and evaluations

No Comments

No Known Activations