INDEX

Explanations

patterns or structures in continuous sequences or series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 abstract

-0.16

ÅĻÃŃÅ¾

-0.15

 Independence

-0.15

tright

-0.15

 independence

-0.15

ÙıÙĪØ§

-0.15

 abstraction

-0.14

AccessException

-0.14

æĬ½

-0.14

 Independ

-0.14

POSITIVE LOGITS

 continuous

0.31

continuous

0.28

Continuous

0.26

 contin

0.25

_continuous

0.25

è¿ŀ

0.25

 Continuous

0.24

 continuum

0.24

 continuity

0.23

 Contin

0.22

Activations Density 0.124%

patterns or structures in continuous sequences or series

No Comments

No Known Activations

patterns or structures in continuous sequences or series

No Comments

No Known Activations