INDEX

Explanations

phrases that indicate duration or continuity over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

agara

-0.16

Ø±Ø§

-0.16

rrha

-0.15

à¸´à¸Ĭ

-0.14

 èĩ

-0.14

è«

-0.14

ouch

-0.14

.scalablytyped

-0.14

legates

-0.13

alse

-0.13

POSITIVE LOGITS

 years

0.22

 decades

0.19

ninger

0.18

 since

0.18

 months

0.18

velle

0.17

decade

0.17

 ÏĩÏģÏĮÎ½Î¹Î±

0.16

 aÃ±os

0.16

 YEARS

0.16

Activations Density 0.089%

phrases that indicate duration or continuity over time

No Comments

No Known Activations